Personalized video recommendation predicts user preference at the video level, while temporal video grounding localizes query-relevant moments. However, strong localization does not establish whether the retrieved moment constitutes valid evidence for recommending the video to a particular user. We study counterfactual behavior-grounded evidence retrieval, which separates where personalized evidence occurs from whether such evidence exists and evaluates whether model predictions respond consistently when that evidence is replaced. We introduce CBGER-10K, containing 5,000 controlled factual--counterfactual pairs for 3,026 users, where each pair replaces only the focal behavior-supported segment while preserving the user, temporal position, and hard distractors. We further propose CBGER, a compact framework that decouples segment-level localization from video-level evidence estimation and learns both through structured counterfactual supervision. CBGER achieves $0.4432$ MRR, $0.6977$ Pair Accuracy, and $0.6987$ Intervention Consistency across five adapted personalized-highlight and temporal-grounding baselines. Notably, compared with QD-DETR, its MRR improvement is not statistically significant, while Pair Accuracy improves by $11.03$ points. These results show that accurate temporal localization does not necessarily imply reliable personalized evidence existence, motivating explicit evaluation of Whether alongside Where.
Mingwen Zhang, Jisheng Dang, Minqiang Yang +3cs.CV cs.CL
Video reasoning tasks such as grounded video question answering and temporal grounding require selecting temporal evidence that supports the query. In many current training setups, temporal supervision is applied through local objectives such as boundary regression or span generation, while verification is used mainly to rerank candidate segments at inference time. We study whether a frozen verifier can also guide training. Our multi-agent framework couples a trainable \emph{Grounder} with a frozen \emph{Verifier}: the Grounder samples candidate trajectories and evidence segments, the Verifier assigns query-conditioned segment scores, a group-relative policy-gradient objective favors trajectories that outperform their within-input peers, and a bootstrapped calibration loss steers temporal predictions toward verifier-preferred spans. Trained on source tasks and evaluated without target-dataset fine-tuning, a two-billion-parameter instantiation transfers zero-shot across grounded question answering, temporal grounding, and long-video question answering, reaching 28.7\% intersection-over-union and 25.4\% answer-grounding accuracy on a grounded-question-answering benchmark, 46.1\% intersection-over-union on a temporal-grounding benchmark, and 54.1\% on a long-video question-answering benchmark. Relative to a strong same-scale baseline, the gains are modest but consistent, with the clearest improvements on relevance-oriented metrics such as intersection-over-union and moderate-overlap recall. Within the tested benchmarks and transfer setting, the results support frozen verification as a training signal for evidence selection, while showing that strict boundary precision remains comparatively weaker. Code and models are available at https://anonymous.4open.science/r/MASIRL-E50C/
We study a critical yet overlooked failure mode in Grounded Video Question Answering: question-invariant grounding, where models predict nearly identical temporal segments for different questions about the same video. We trace this behavior to two structural limitations in prior common designs: (i) modality isolation that fixes video representations before they receive question semantics, and (ii) weak question injection inside the grounding module. To address this, we propose GroundFormer, which conditions video features on question intent before localization via learnable communication tokens that mediate directed visuo-lingual interaction. On top of the question-conditioned features, a factorized MIL cross-attention couples answer selection with temporal evidence under candidate-level supervision, while Gaussian smoothing converts peaked attention into temporally coherent segments. We further introduce a hierarchical multi-modal contrastive loss that aligns video, question, and answer embeddings across a two-pass training pipeline. GroundFormer achieves state-of-the-art grounded VideoQA performance on NExT-GQA and STAR, substantially improving question-discriminative temporal grounding.
Recent advances in video generation models have significantly improved the realism of synthetic videos, blurring the boundary between generated and authentic content and raising concerns about misinformation. Existing MLLM-based detectors mainly rely on supervised fine-tuning or label-level reinforcement learning, where coarse supervision limits generalization to unseen scenarios and emerging video generators. To overcome these limitations, we are the first to introduce \textbf{meta-detection} into AI-generated video detection, enabling reliable forgery detection by jointly optimizing predicted labels and supporting evidence within reinforcement learning. This paradigm requires reliable evidence signals and effective mechanisms to integrate them into label-level optimization. Textual rationales provide semantic descriptions of forgery artifacts, but their generation and verification depend on external models, making supervision vulnerable to hallucinations and semantic biases. In contrast, temporal grounding provides more objective and verifiable evidence, as manipulated intervals can be precisely controlled during forgery construction. Based on this insight, we propose an automated data construction pipeline that generates paired real-fake videos by replacing temporal segments with boundary-frame-conditioned video generation models. Furthermore, we introduce \textbf{Evidence-Guided Reward Redistribution}, which performs evidence-aware credit assignment by redistributing rewards among label-correct responses according to evidence quality. This preserves reliable label supervision while encouraging detectors to acquire fine-grained and verifiable forgery localization capabilities. Extensive experiments demonstrate that \textbf{VidForensics-M1} effectively leverages verifiable temporal evidence to achieve robust and generalizable AI-generated video detection.
Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimodal large language models (MLLMs) provide a natural interface for this task, but existing work typically assigns one or more labels to an entire clip. Such clip-level recognition overlooks two defining properties of real camera motion: it can change within a shot, and multiple movements can occur simultaneously. We therefore formulate camera-motion understanding as temporally grounded, compositional recognition, which requires a model to localize motion-consistent intervals and identify every movement active within each interval. We introduce CamChoreo, a benchmark of 4,229 real single-shot clips with expert-annotated temporal segments. Its annotations use a compact vocabulary of 20 direction-aware labels, and nearly half of the segments contain compound camera motion, with multiple movement primitives active simultaneously. Recognizing such fine-grained, compositional motion is hard for current MLLMs, whose visual encoders emphasize semantic content rather than the geometric evidence on which camera motion depends. Directly injecting features from a frozen 3D foundation model addresses this gap, but requires running the expensive geometry model on every input; we refer to this baseline as CamInject. We instead propose CamDistill, which distills the same geometric knowledge into lightweight camera tokens during training and removes the 3D model at inference. CamDistill matches the accuracy of direct feature injection without running the 3D teacher at inference. Together, CamChoreo and CamDistill advance camera-motion understanding from clip-level labeling to temporally grounded, compositional recognition. Project page: https://ddz16.github.io/cammotion.github.io/.
Fitness Action Quality Assessment (AQA) is important for intelligent sports training, yet the capabilities of Multimodal Large Language Models (MLLMs) in this setting remain underexplored. Existing benchmarks rely on action-specific annotation schemes and focus primarily on final assessment outputs, offering limited insight into how models assess exercise quality. We introduce FitAQA, a systematic benchmark for evaluating MLLMs in fitness AQA, containing 2,219 videos and 5,512 QA instances across 30 bodyweight exercises. In collaboration with experts in sports science, we develop a unified form error taxonomy that defines 38 recurring form errors within six complementary quality dimensions: alignment, symmetry, stability, coordination, tempo, and completeness. This taxonomy provides a shared assessment framework across different exercises. FitAQA further formulates three evaluation tasks: perception for recognizing relevant visual evidence, judgement for combining that evidence with domain knowledge to assess execution correctness, and temporal grounding for localizing form errors over time. Extensive evaluation shows that current MLLMs still struggle to assess exercise quality comprehensively and localize form errors precisely. Controlled experiments further indicate that visual perception is a key bottleneck, as judgement performance improves substantially when ground-truth perceptual evidence is provided. The dataset and evaluation code will be made publicly available.
Multimodal LLMs that recognise events reliably still fail to say when they happen. Prompted for timestamps, strong VLMs reach as little as $3.8\%$ R@0.5 on Charades-STA, and $77$ to $80\%$ of their wrong predictions carry low output entropy: the models are confidently wrong, and entropy-based error detection stays below a random classifier. We show that this failure lives in the task interface, not in perception. Holding the weights fixed, replacing timestamp regression with a coarse-to-fine scan of binary questions, whose first-token probabilities are consumed only as a ranking, raises R@0.5 by $28$ to $50$ points across four frozen backbones. The residual failures decompose into two measurable axes: a perception axis that moves with the backbone, and a geometry axis that is analytically predictable from the ratio of the output-window and event widths. FV-Action, the training-free method built on this analysis, reaches $56.8\%$ R@0.5 on Charades-STA, above the same backbone's native grounding pipeline and the strongest training-free result on this benchmark; it surpasses every TVG-trained model evaluated zero-shot on TACoS, and improves over direct prediction on ActivityNet Captions and QVHighlights, with no temporal supervision at any stage.
Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals. Existing approaches exhibit a "when-what" dissociation: traditional DNN-based methods localize when anomalies occur but lack semantic understanding, whereas LLM-based methods explain what happens but neglect precise temporal grounding. We attribute this to the absence of a unified reasoning paradigm. Inspired by how humans inspect surveillance videos - glancing globally to form temporal hypotheses, scrutinizing suspicious segments, and thinking iteratively to correct errors - we study this global-to-local paradigm from two perspectives. We first propose Glance then Scrutinize (GtS), a training-free framework using static and dynamic textual guidance for coarse-to-fine anomaly grounding and understanding, balancing accuracy and speed. To break the ceiling imposed by frozen external modules, we further propose a tool-augmented agentic VAD method, where a multimodal large language model learns to invoke a video cropping tool, inspect densely resampled frames, and self-correct mislocalized hypotheses, via cold-start supervised fine-tuning followed by reinforcement learning with a joint answer-grounding reward. For training and evaluation, we extend our prior VAGU benchmark into VAGU-T (Video Anomaly Grounding, Understanding, and Thinking), comprising 7,567 real-world videos over 21 anomaly categories with human-validated grounding, explanations, QA pairs, and chain-of-thought tool-calling traces. We further introduce JeAUG, a metric jointly evaluating semantic interpretability and temporal precision. Experiments show that GtS substantially surpasses training-free baselines, while the agentic model delivers both higher accuracy and faster inference.
Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve with uniformly high-fidelity inputs. We introduce OmniReasoner, a tool-use post-training framework for Thinking with Long Audio-Video: omni-modal LLMs learn, via supervised fine-tuning and reinforcement learning, to decide whether and where to call a zoom-in tool before answering. OmniReasoner first builds a low-cost global preview of the full stream and then, when needed, calls the zoom-in tool with a requested temporal interval for higher-fidelity visual and audio inspection before answering. Because the model observes different sampling granularities before and after this call -- a sparse global preview and a denser local clip -- we introduce TimeAnchor, which keeps the tool's temporal argument valid and round-trip-consistent across these granularities, rather than tied to frame indices from a particular sampling rate. To make this tool-use behavior trainable without expensive manual interval annotation, we build a Temporal Augmented Data Engine that synthesizes tool-use post-training trajectories by video editing and composition. Experiments across omnimodal and video benchmarks show that OmniReasoner improves both answer accuracy and temporal grounding while concentrating high-fidelity computation on informative regions. Code is available at https://github.com/RockyChen0205/OmniReasoner.
Grounded long-video question answering (Grounded LVQA) requires answering a question about a long video while localizing the short evidence interval that supports the answer. Recent agentic methods frame this task as multi-turn exploration with a single crop_video(start, end) action, which supports coarse-to-fine narrowing but provides no primitive for fine-to-coarse backtracking. As a result, these agents typically converge prematurely and cannot recover from an early mistake. We propose VideoTreeSearch (VTS), a framework that casts grounded LVQA as iterative self-correcting search over an adaptive temporal tree. VTS constructs a non-uniform tree from visual scene boundaries so that each node corresponds to a semantically coherent segment, and trains an agent to navigate the tree through four discrete operations: zoom_in, zoom_out, shift, and answer. These operations expose backtracking and recovery as explicit, learnable primitives rather than implicit behaviors. To train this navigation, we introduce a trajectory synthesis pipeline that produces multi-step paths through the tree, including deliberate detours into incorrect branches followed by recovery. We use these trajectories for supervised fine-tuning, followed by reinforcement learning with grounding and answer-accuracy rewards. On three Grounded LVQA benchmarks (CG-Bench, Haystack-LVBench, Haystack-Ego4D), VTS outperforms the strongest prior agentic methods by +12.5 mIoU on CG-Bench and +7.4 T-F1 on Haystack-Ego4D. The learned policy also transfers to general long-video QA, surpassing all prior agentic baselines on Video-MME, MLVU, and LVBench by up to +7.1 accuracy points. Ablations confirm that self-correcting hierarchical search is the central mechanism behind these gains: removing either adaptive descent or explicit backtracking substantially degrades performance. Code is available at https://github.com/CeeZh/VTS.
Aleksandr Kutsakov, Mariia Sadovina, Georgii Gospodinov +4eess.AS cs.CL
Temporal grounding in long recordings remains challenging for audio-conditioned LLMs. We present a time-aware audio LLM that answers questions with explicit timestamps over up to 120 minutes of input. Our approach interleaves periodic time markers with continuous audio tokens using large-scale synthetic supervision from a cascaded pipeline. Our model achieves strong temporal-grounding accuracy on short and long benchmarks and supports time-anchored fragment descriptions and summaries. Extensive ablations examine how time representation, marker frequency, tokenization, and duration-mixture design affect accuracy and computational cost. We release model weights and datasets to support further research on time-aware audio understanding, available at https://huggingface.co/ai-sage/GigaChat3.1-Audio-10B-A1.8B.
Video reasoning requires models to identify and verify temporally localized evidence within long video sequences. Recent Video Large Language Models (Video-LLMs) have shown promising reasoning abilities when aligned with reinforcement learning, yet existing approaches typically rely on outcome-based rewards that supervise only the final prediction. Such supervision provides limited guidance on how models should discover the relevant temporal evidence during intermediate reasoning. In this work, we propose TimeThink, a reinforcement learning framework that explicitly guides temporal evidence discovery in Video-LLMs. Our key idea is to treat temporal clue steps as the fundamental optimization primitive of video reasoning, where each reasoning step references a candidate time interval in the video. We introduce a step-wise temporal process reward that provides localized credit assignment for these clues and a joint process--outcome optimization objective that balances reasoning fidelity with task correctness. To enable scalable training, we construct TimeThink-RFT-20K, a dataset with automatically derived temporal evidence segments. Extensive experiments across video reasoning, temporal grounding, and general video understanding benchmarks show that TimeThink consistently improves both temporal localization and reasoning performance, achieving state-of-the-art results among open-source video RL models.
Long-video reasoning is fundamentally constrained by how models acquire and utilize visual evidence. Existing tool-augmented video frameworks often interleave temporal grounding and answer reasoning within a single trajectory, causing early semantic hypotheses to bias evidence localization. We term this failure mode premature semantic commitment, where biased grounding retrieves incomplete evidence and incomplete evidence further reinforces incorrect reasoning. To address this issue, we propose EFlow, an evidence-first video reasoning framework built upon Qwen3-VL. EFlow explicitly separates temporal grounding and logical reasoning through CoT for Temporal Grounding and CoT for Reasoning, enabling the model to retrieve relevant evidence before answer inference. In addition, EFlow introduces a confidence-aware reflection mechanism that re-evaluates the full video when retrieved evidence is potentially insufficient. We further construct dedicated trajectory datasets and train EFlow through supervised fine-tuning, reinforcement learning, and reinforcement fine-tuning. Extensive experiments across five video understanding benchmarks demonstrate that EFlow consistently improves long-video reasoning performance.
As video corpora continue to expand in both scale and task complexity, there is increasing demand for approaches that retrieve relevant videos from large-scale corpora (inter-video reasoning) and subsequently perform fine-grained, query-conditioned tasks (intra-video reasoning) within the retrieved content, such as temporal grounding. However, existing approaches typically treat retrieval as a preprocessing step, and consequently, when the initial retrieval fails, there is no mechanism to refine the search, leading to the failure of subsequent fine-grained intra-video reasoning. Moreover, while recent agentic frameworks have advanced video understanding, they typically assume that the query-relevant video is already given, focusing exclusively on intra-video reasoning tasks. To address these limitations, we propose VideoSearch-R1, an agentic framework for iterative video retrieval and reasoning through multi-turn interaction with a video search engine. Specifically, we introduce Soft Query Refinement (SQR) to refine search query tokens in a continuous latent space rather than rewriting queries in the discrete text space, enabling more efficient and fine-grained adjustments. SQR and its reasoning process are trained using Group Relative Policy Optimization (GRPO), guided by task-level reward signals derived from retrieval and downstream tasks. Building upon this, VideoSearch-R1 achieves state-of-the-art performance across three datasets on Video Corpus Moment Retrieval (VCMR), iteratively retrieving videos from large-scale corpora, refining search queries, and performing precise query-conditioned temporal grounding within the retrieved content. Our analyses show that SQR effectively refines the original query, requiring significantly fewer generated tokens than explicit text-level query refinement. Code and model checkpoints are publicly available at mlvlab.github.io/VideoSearch-R1.
Zeynep Yılbırt, Marina Litvak, Michael Färbercs.CL cs.IR
Meeting archives are difficult to search when users remember what was discussed but not when. We study topic-to-timestamp alignment: given a natural-language topic and a timestamped meeting transcript, the goal is to return the time at which the topic is discussed. A standard RAG setup can retrieve relevant transcript excerpts, but still asks the language model to generate a timestamp, which can produce unsupported or invalid timecodes. We therefore recast timestamp prediction as constrained temporal candidate selection: the system retrieves timestamped transcript chunks, and the model selects the candidate that best grounds the topic instead of generating a timecode. On 420 topic-timestamp queries from 200 municipal meeting transcripts, this increases Recall@5 from 31.9% to 50.0%, reduces MAE from 837.0 seconds to 761.0 seconds with Mistral-7B-Instruct, and increases the number of parseable outputs from 373 to 419 of 420 queries. The results suggest that temporal grounding in long transcripts depends strongly on retrieval quality and output design, not only on the choice of the language model.
Temporal grounding--returning the interval $[t_s, t_e]$ for a natural-language query over a video--is the language interface to long-form video, yet has been studied on short videos; the dynamics of hour-scale natural-language grounding remain underexplored. We take the position that at hour-scale, the binding constraint is search, not recognition: Video-LLMs are bottlenecked not by localizing a nearby event, but--given a natural-language query--by searching for the relevant region of a long video. To test this, we release ExtremeWhenBench, the first open hour-scale grounding benchmark (2,273 queries over 194 videos, mean 75.7 min, max 9 hr) with an open-form query distribution. Every open Video-LLM collapses while a frame-level retrieval baseline outperforms them; a failure taxonomy attributes 85% of failures to search; and a retrieve-then-ground hybrid recovers 6.7x over the monolithic Video-LLM--mirroring retrieve-then-read in open-domain QA.
The task of temporal answer grounding in instructional video (TAGV), which aims to locate precise video segments that respond to natural language queries, is increasingly important for direct video answer retrieval. This task remains challenging due to the need to comprehend semantically complex questions and to address the significant length mismatch between untrimmed videos and short target moments. Existing methods often suffer from sensitivity to irrelevant content or insufficient visual reasoning capabilities. To tackle these limitations, we propose a Candidate-Aware Causal Reasoning (CACR) framework. Our approach first employs a Visual-Language Pre-training based Candidate Selection (VBCS) algorithm to efficiently generate K candidate segments, then applies a temporal logic reasoning module enhanced by a rejection reward mechanism and optimized via Group Relative Policy Optimization (GRPO) for robust inference. Extensive experiments on six benchmarks demonstrate that our method achieves state-of-the-art performance in terms of mean Intersection-over-Union (mIoU), providing a new perspective for reasoning-based retrieval in long videos.
This paper presents our system description for the 2nd Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR). Addressing the critical challenges of cross-lingual long-video comprehension, strict persona adherence, and zero-hallucination temporal grounding, we propose a fully training-free, two-stage cascaded Video RAG pipeline. Our architecture strategically decouples semantic retrieval from cognitive logical reasoning through a modality-aware division of labor. In the first stage, a high-recall semantic pre-fetching module employs dense retrieval using only high-fidelity visual summaries and global text descriptions, explicitly isolating noisy modalities (e.g., OCR and ASR) to maintain a pristine vector space. In the second stage, an Adaptive, Iterative, and Reasoning-based (A.I.R.) filtering agent, powered by a commercial Large Language Model (LLM), performs fine-grained cognitive reranking. The agent re-incorporates full multimodal contexts to enforce strict logical alignment with user personas, effectively pruning semantically similar but logically irrelevant candidates. Finally, a Prompt Sculpting mechanism constrains the generator to synthesize the distilled subset into strictly formatted JSON responses with exact chunk-level citations. Evaluated on the RAG track, our resource-aware approach shows exceptional precision in both information retrieval and persona-conditioned generation.
Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, however, often require localizing multiple disjoint segments for a single query -- a setting we term One-to-Many Temporal Grounding (OMTG). Previous state-of-the-art MLLMs, optimized for one-to-one settings, struggle in this context, often yielding near-zero scores due to a lack of event cardinality perception. To bridge this gap, we present a systematic solution with three key contributions. First, we establish the first comprehensive OMTG benchmark, introducing Count Accuracy (C-Acc) and Effective Temporal F1 (EtF1) as evaluation metrics. Second, we curate a high-quality OMTG dataset comprising 56k samples through a sophisticated construction pipeline. Third, we develop novel temporal and caption reward functions specifically designed for OMTG. In particular, the caption reward leverages Chain-of-Thought reasoning over dense video captions to explicitly guide policy optimization toward both preciseness and completeness. Extensive experiments show our model achieves a new state-of-the-art EtF1 of 43.65\% on OMTG Bench, outperforming Gemini 2.5 Pro and Seed-1.8 by 15.85\% and 15.61\%, respectively. Project Page: https://insomniaaac.github.io/OMTG/
MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning. MOSS-Audio couples a dedicated audio encoder with a modality adapter and a large language model: the encoder produces 12.5 Hz temporal representations, the adapter projects them into the decoder space, and the decoder generates autoregressive text outputs. Two design choices are central to the system: \textbf{DeepStack cross-layer feature injection}, which exposes the decoder to acoustic information from multiple encoder depths, and \textbf{time markers}, which provide explicit temporal cues by inserting timestamp markers into the audio-token stream. At the data level, we design an event-preserving audio annotation pipeline that segments raw audio at coherent event boundaries, applies branch-specific annotation to speech, music, and general audio, and merges the results into unified captions for pretraining. The intermediate branch-specific captions are further retained to support the construction of task-oriented SFT data. The model is pretrained on large-scale audio-language data, with time-aware objectives incorporated to support temporal grounding, and then undergoes multi-stage post-training to enhance instruction following and audio-grounded reasoning. We release 4B and 8B variants in both Instruct and Thinking configurations. MOSS-Audio achieves strong performance across general audio understanding, speech captioning, ASR, and timestamped ASR, positioning it as a promising understanding foundation for future voice agents.
In this report, we present our champion solutions for the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge at CVPR 2026. Both tracks require accurately localizing temporal segments from long untrimmed egocentric videos. To address these tasks, we propose a reranking-based framework that effectively leverages the strong video-language reasoning capability of multimodal large language model (MLLM) while preserving the efficiency and candidate recall of conventional localization pipelines. Specifically, we first obtain a set of candidate segments from existing localization model OSGNet, and then employ MLLM to select the segment that best matches the given query, thereby refining the final prediction. Ultimately, our method achieved first place in both the Natural Language Queries and GoalStep tracks. Our code can be found at https://github.com/iLearn-Lab/CVPR25-OSGNet.
Long-term video understanding requires interpreting complex temporal events and reasoning over procedural activities. While instructional video corpora, like HowTo100M, offer rich resources for model training, they present significant challenges, including noisy ASR transcripts and inconsistent temporal alignments between narration and visual content. In this work, we introduce an automated, training-free pipeline to extract high-quality procedural annotations from in-the-wild instructional videos. Our approach segments videos into coherent shots, filters poorly aligned content, and leverages state-of-the-art multimodal and large language models (Qwen2.5-VL and DeepSeek-R1) to generate structured, temporally grounded procedural steps. This pipeline yields DenseStep2M, a large-scale dataset comprising approximately 100K videos and 2M detailed instructional steps, designed to support comprehensive long-form video understanding. To rigorously evaluate our pipeline, we curate DenseCaption100, a benchmark of high-quality, human-written captions. Evaluations demonstrate strong alignment between our auto-generated steps and human annotations. Furthermore, we validate the utility of DenseStep2M across three core downstream tasks: dense video captioning, procedural step grounding, and cross-modal retrieval. Models fine-tuned on DenseStep2M achieve substantial gains in captioning quality and temporal localization, while exhibiting robust zero-shot generalization across egocentric, exocentric, and mixed-perspective domains. These results underscore the effectiveness of DenseStep2M in facilitating advanced multimodal alignment and long-term activity reasoning. Our dataset is available at https://huggingface.co/datasets/mingjige/DenseStep2M.
Runze Cui, Fangxin Shang, Yehui Yang +2cs.CV cs.CE cs.MM
Document understanding is a critical capability in financial credit review, onboarding, and remote verification, where both decision accuracy and evidence traceability matter. Compared with static document images, document videos present a temporally redundant and sequentially unfolding evidence stream, require evidence integration across frames, and preserve acquisition-process cues relevant to authenticity-sensitive and anti-fraud review. We introduce FCMBench-Video, a benchmark for document-video intelligence that evaluates document perception, temporal grounding, and evidence-grounded reasoning under realistic capture conditions. For privacy-compliant yet realistic data at scale, we organize construction as an atomic-acquisition and composition workflow that records reusable single-document clips, applies controlled degradations, and assembles long-form multi-document videos with prescribed temporal spans. FCMBench-Video is built from 495 atomic videos composed into 1,200 long-form videos paired with 11,322 expert-annotated question--answer instances, covering 28 document types over 20s--60s duration tiers and 5,960 Chinese / 5,362 English instances. Evaluations on nine recent Video-MLLMs show that FCMBench-Video provides meaningful separation across systems and capabilities: counting is the most duration-sensitive task, Cross-Document Validation and Evidence-Grounded Selection probe higher-level evidence integration, and Visual Prompt Injection provides a complementary robustness dimension. The overall score distribution is broad and approximately bell-shaped, indicating a benchmark that is neither saturated nor dominated by trivial cases. Together, these results position FCMBench-Video as a reproducible benchmark for tracking Video-MLLM progress on document-video understanding and probing capability boundaries in authenticity-sensitive credit-domain applications.