{"total":51,"rows":[{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153,"area":"lr"},{"id":"2312.14115","title":"LingoQA: Visual Question Answering for Autonomous Driving","created":"2023-12-21","cited_by_count":145,"area":"mllm"},{"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":"2503.11495","title":"V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning","created":"2025-03-14","cited_by_count":68,"area":"lr"},{"id":"2404.10241","title":"Vision-and-Language Navigation via Causal Learning","created":"2024-04-16","cited_by_count":51,"area":null},{"id":"2303.14369","title":"Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning","created":"2023-03-25","cited_by_count":45,"area":null},{"id":"2506.09943","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","created":"2025-06-11","cited_by_count":35,"area":"lr"},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32,"area":null},{"id":"2503.13502","title":"Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey","created":"2025-03-12","cited_by_count":24,"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":"2502.12425","title":"Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning","created":"2025-02-18","cited_by_count":20,"area":"lr"},{"id":"2501.08326","title":"Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks","created":"2025-01-14","cited_by_count":17,"area":"mllm"},{"id":"2305.04224","title":"Visual Causal Scene Refinement for Video Question Answering","created":"2023-05-07","cited_by_count":16,"area":null},{"id":"2407.01872","title":"Referring Atomic Video Action Recognition","created":"2024-07-02","cited_by_count":16,"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":"2404.01299","title":"CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes","created":"2024-04-01","cited_by_count":13,"area":"lr"},{"id":"2412.01798","title":"SEAL: Semantic Attention Learning for Long Video Representation","created":"2024-12-02","cited_by_count":13,"area":null},{"id":"2509.11866","title":"Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding","created":"2025-09-15","cited_by_count":13,"area":null},{"id":"2305.04530","title":"A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues","created":"2023-05-08","cited_by_count":11,"area":"lr"},{"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":"2412.05725","title":"Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events","created":"2024-12-07","cited_by_count":9,"area":"lr"},{"id":"2407.03788","title":"MAMA: Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2504.04550","title":"Advancing Egocentric Video Question Answering with Multimodal Large Language Models","created":"2025-04-06","cited_by_count":8,"area":"lr"},{"id":"2308.03267","title":"Redundancy-aware Transformer for Video Question Answering","created":"2023-08-07","cited_by_count":7,"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":"2503.21055","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","created":"2025-03-27","cited_by_count":6,"area":null},{"id":"2505.04147","title":"R^3-VQA: \"Read the Room\" by Video Social Reasoning","created":"2025-05-07","cited_by_count":6,"area":"lr"},{"id":"2505.19474","title":"Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models","created":"2025-05-26","cited_by_count":4,"area":"mllm"},{"id":"2506.21154","title":"Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimation","created":"2025-06-26","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":"2506.07811","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2605.30346","title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2503.15807","title":"Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2602.14705","title":"It's a Matter of Time: Three Lessons on Long-Term Motion for Perception","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2605.03276","title":"VEBench:Benchmarking Large Multimodal Models for Real-World Video Editing","created":"2026-05-05","cited_by_count":2,"area":"lr"},{"id":"2310.06627","title":"What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models","created":"2023-10-10","cited_by_count":1,"area":"lr"},{"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":"2508.21010","title":"ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering","created":"2025-08-28","cited_by_count":1,"area":"lr"},{"id":"2512.24323","title":"Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2605.08175","title":"KARMA-MV: A Benchmark for Causal Question Answering on Music Videos","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2605.09422","title":"Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs","created":"2026-05-10","cited_by_count":1,"area":"mllm"},{"id":"2605.31529","title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2310.18369","title":"Apollo: Zero-shot MultiModal Reasoning with Multiple Experts","created":"2023-10-25","cited_by_count":0,"area":"lr"},{"id":"2403.03405","title":"Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigation","created":"2024-03-06","cited_by_count":0,"area":"safety"},{"id":"2403.07198","title":"Action Reimagined: Text-to-Pose Video Editing for Dynamic Human Actions","created":"2024-03-11","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":"2505.24346","title":"VUDG: A Dataset for Video Understanding Domain Generalization","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2607.26518","title":"EgoSafe: A First-Person Mobile-Captured Benchmark for Visual Safety Understanding","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.08273","title":"Action- and Language-Conditioned Video Assessment for Embodied Control","created":"2026-08-08","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":"2608.30068","title":"TAKE 85: Testing Audiovisual filmmaKer's intEnt across 85 Hours of Film","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}