{"total":68,"rows":[{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109,"area":"mllm"},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615,"area":"mllm"},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135,"area":null},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68,"area":null},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"id":"2203.11654","title":"Fine-Grained Scene Graph Generation with Data Transfer","created":"2022-03-22","cited_by_count":57,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42,"area":null},{"id":"2401.01505","title":"Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports","created":"2024-01-03","cited_by_count":41,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"area":null},{"id":"2406.05615","title":"Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives","created":"2024-06-09","cited_by_count":37,"area":null},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2306.11732","title":"Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models","created":"2023-06-15","cited_by_count":27,"area":null},{"id":"2403.16998","title":"Understanding Long Videos with Multimodal Language Models","created":"2024-03-25","cited_by_count":25,"area":"mllm"},{"id":"2207.12783","title":"Equivariant and Invariant Grounding for Video Question Answering","created":"2022-07-26","cited_by_count":22,"area":null},{"id":"2312.03050","title":"HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding","created":"2023-12-05","cited_by_count":22,"area":null},{"id":"2307.12058","title":"Discovering Spatio-Temporal Rationales for Video Question Answering","created":"2023-07-22","cited_by_count":21,"area":null},{"id":"2208.08965","title":"GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement","created":"2022-08-18","cited_by_count":20,"area":null},{"id":"2203.08013","title":"End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2312.12816","title":"Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering","created":"2023-12-20","cited_by_count":19,"area":null},{"id":"2212.05765","title":"Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue","created":"2022-12-12","cited_by_count":18,"area":null},{"id":"2212.09381","title":"Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark","created":"2022-12-19","cited_by_count":16,"area":null},{"id":"2304.08682","title":"Learning Situation Hyper-Graphs for Video Question Answering","created":"2023-04-18","cited_by_count":16,"area":null},{"id":"2305.04224","title":"Visual Causal Scene Refinement for Video Question Answering","created":"2023-05-07","cited_by_count":16,"area":null},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15,"area":null},{"id":"2401.10711","title":"Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering","created":"2024-01-19","cited_by_count":14,"area":"mllm"},{"id":"2301.11507","title":"Semi-Parametric Video-Grounded Text Generation","created":"2023-01-27","cited_by_count":13,"area":null},{"id":"2312.04931","title":"Long Video Understanding with Learnable Retrieval in Video-Language Models","created":"2023-12-08","cited_by_count":9,"area":null},{"id":"2407.03008","title":"Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering","created":"2024-07-03","cited_by_count":9,"area":"lr"},{"id":"2312.00347","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","created":"2023-12-01","cited_by_count":8,"area":null},{"id":"2401.01529","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","created":"2024-01-03","cited_by_count":8,"area":null},{"id":"2405.19723","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2308.03267","title":"Redundancy-aware Transformer for Video Question Answering","created":"2023-08-07","cited_by_count":7,"area":null},{"id":"2210.11109","title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2212.13163","title":"MRTNet: Multi-Resolution Temporal Network for Video Sentence Grounding","created":"2022-12-26","cited_by_count":6,"area":null},{"id":"2304.03754","title":"Language Models are Causal Knowledge Extractors for Zero-shot Video Question Answering","created":"2023-04-07","cited_by_count":6,"area":null},{"id":"2303.03131","title":"Video Question Answering Using CLIP-Guided Visual-Text Attention","created":"2023-03-06","cited_by_count":5,"area":null},{"id":"2307.04192","title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","created":"2023-07-09","cited_by_count":5,"area":null},{"id":"2310.19516","title":"Generating Context-Aware Natural Answers for Questions in 3D Scenes","created":"2023-10-30","cited_by_count":5,"area":null},{"id":"2412.12833","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","created":"2024-12-17","cited_by_count":5,"area":"mllm"},{"id":"2302.02136","title":"Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer","created":"2023-02-04","cited_by_count":4,"area":null},{"id":"2307.13250","title":"Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2309.02290","title":"ATM: Action Temporality Modeling for Video Question Answering","created":"2023-09-05","cited_by_count":3,"area":"lr"},{"id":"2406.18538","title":"VideoQA-SC: Adaptive Semantic Communication for Video Question Answering","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2210.03941","title":"Learning Fine-Grained Visual Understanding for Video Question Answering via Decoupling Spatial-Temporal Modeling","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2401.01510","title":"Answering from Sure to Uncertain: Uncertainty-Aware Curriculum Learning for Video Question Answering","created":"2024-01-03","cited_by_count":2,"area":null},{"id":"2409.07747","title":"Multi-object event graph representation learning for Video Question Answering","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2511.20190","title":"SFA: Scan, Focus, and Amplify toward Guidance-aware Answering for Video TextVQA","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2406.10923","title":"Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies","created":"2024-06-16","cited_by_count":1,"area":"lr"},{"id":"2410.05767","title":"Grounding is All You Need? Dual Temporal Grounding for Video Dialog","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2204.11544","title":"Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2412.09230","title":"Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2501.08771","title":"Admitting Ignorance Helps the Video Question Answering Models to Answer","created":"2025-01-15","cited_by_count":0,"area":null},{"id":"2504.02417","title":"Leveraging Static Relationships for Intra-Type and Inter-Type Message Passing in Video Question Answering","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2504.05783","title":"Video Flow as Time Series: Discovering Temporal Consistency and Variability for VideoQA","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2507.09200","title":"THYME: Temporal Hierarchical-Cyclic Interactivity Modeling for Video Scene Graphs in Aerial Footage","created":"2025-07-12","cited_by_count":0,"area":null},{"id":"2508.03039","title":"VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2510.20285","title":"DMC$^3$: Dual-Modal Counterfactual Contrastive Construction for Egocentric Video Question Answering","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.20201","title":"GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2603.14953","title":"Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering","created":"2026-03-16","cited_by_count":0,"area":"mllm"},{"id":"2606.09181","title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.23330","title":"IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.21386","title":"AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents","created":"2026-09-18","cited_by_count":0,"area":"agents"}],"next_cursor":null}