{"total":68,"rows":[{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615,"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":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63,"area":null},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2206.07869","title":"Let Invariant Rationale Discovery Inspire Graph Contrastive Learning","created":"2022-06-16","cited_by_count":57,"area":null},{"id":"2207.12647","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","created":"2022-07-26","cited_by_count":57,"area":"lr"},{"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":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44,"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":"2503.06169","title":"Treble Counterfactual VLMs: A Causal Approach to Hallucination","created":"2025-03-08","cited_by_count":35,"area":"mllm"},{"id":"2403.19600","title":"Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model","created":"2024-03-28","cited_by_count":34,"area":"diffusion"},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32,"area":null},{"id":"2308.15985","title":"Vision-Based Traffic Accident Detection and Anticipation: A Survey","created":"2023-08-30","cited_by_count":31,"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":"2207.12783","title":"Equivariant and Invariant Grounding for Video Question Answering","created":"2022-07-26","cited_by_count":22,"area":null},{"id":"2403.17935","title":"OmniVid: A Generative Framework for Universal Video Understanding","created":"2024-03-26","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":"2207.11652","title":"Counterfactual Reasoning for Out-of-distribution Multimodal Sentiment Analysis","created":"2022-07-24","cited_by_count":18,"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":"2502.12638","title":"NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation","created":"2025-02-18","cited_by_count":17,"area":"diffusion"},{"id":"2212.09381","title":"Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmark","created":"2022-12-19","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":"2211.11446","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","created":"2022-11-21","cited_by_count":15,"area":null},{"id":"2412.05818","title":"SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation","created":"2024-12-08","cited_by_count":15,"area":"mllm"},{"id":"2308.16187","title":"Boosting Detection in Crowd Analysis via Underutilized Output Features","created":"2023-08-30","cited_by_count":14,"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":"2307.13992","title":"Causal reasoning in typical computer vision tasks","created":"2023-07-26","cited_by_count":12,"area":"lr"},{"id":"2406.05814","title":"TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models","created":"2024-06-09","cited_by_count":12,"area":"mllm"},{"id":"2503.07635","title":"Cross-modal Causal Relation Alignment for Video Question Grounding","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2504.13621","title":"Visual Intention Grounding for Egocentric Assistants","created":"2025-04-18","cited_by_count":11,"area":null},{"id":"2403.11463","title":"Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding","created":"2024-03-18","cited_by_count":10,"area":null},{"id":"2409.10262","title":"Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation","created":"2024-09-16","cited_by_count":10,"area":null},{"id":"2308.03282","title":"Environment-Invariant Curriculum Relation Learning for Fine-Grained Scene Graph Generation","created":"2023-08-07","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":"2504.07519","title":"VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding","created":"2025-04-10","cited_by_count":9,"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":"2308.03267","title":"Redundancy-aware Transformer for Video Question Answering","created":"2023-08-07","cited_by_count":7,"area":null},{"id":"2404.11111","title":"CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation","created":"2024-04-17","cited_by_count":7,"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":"2305.10049","title":"TG-VQA: Ternary Game of Video Question Answering","created":"2023-05-17","cited_by_count":6,"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":"2409.14319","title":"Scene-Text Grounding for Text-Based Video Question Answering","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2410.09380","title":"Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering","created":"2024-10-12","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":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2507.14784","title":"LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering","created":"2025-07-20","cited_by_count":4,"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":"2410.09379","title":"Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2304.08083","title":"VCD: Visual Causality Discovery for Cross-Modal Question Reasoning","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2305.03971","title":"Adaptive loose optimization for robust question answering","created":"2023-05-06","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":"2506.10002","title":"EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis","created":"2025-03-16","cited_by_count":2,"area":null},{"id":"2506.23263","title":"Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis","created":"2025-06-29","cited_by_count":2,"area":"diffusion"},{"id":"2604.01460","title":"Reinforcing Consistency in Video MLLMs with Structured Rewards","created":"2026-04-01","cited_by_count":2,"area":"mllm"},{"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":"2407.20257","title":"Causal Understanding For Video Question Answering","created":"2024-07-23","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":"2505.24346","title":"VUDG: A Dataset for Video Understanding Domain Generalization","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2603.11689","title":"Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"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}],"next_cursor":null}