{"total":96,"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":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2207.02803","title":"Delving into Sequential Patches for Deepfake Detection","created":"2022-07-06","cited_by_count":41,"area":null},{"id":"2203.17251","title":"Continuous Scene Representations for Embodied AI","created":"2022-03-31","cited_by_count":39,"area":null},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39,"area":null},{"id":"2212.04155","title":"Latent Graph Representations for Critical View of Safety Assessment","created":"2022-12-08","cited_by_count":37,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2207.05515","title":"Compound Prototype Matching for Few-shot Action Recognition","created":"2022-07-12","cited_by_count":35,"area":null},{"id":"2112.09828","title":"Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs","created":"2021-12-18","cited_by_count":31,"area":null},{"id":"2202.09277","title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","created":"2022-02-18","cited_by_count":30,"area":null},{"id":"2403.12418","title":"STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model","created":"2024-03-19","cited_by_count":24,"area":"ssm"},{"id":"2112.04222","title":"Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs","created":"2021-12-08","cited_by_count":23,"area":null},{"id":"2206.04727","title":"STNDT: Modeling Neural Population Activity with a Spatiotemporal Transformer","created":"2022-06-09","cited_by_count":23,"area":null},{"id":"2211.16636","title":"Iterative Scene Graph Generation with Generative Transformers","created":"2022-11-30","cited_by_count":22,"area":null},{"id":"2302.00268","title":"Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection","created":"2023-02-01","cited_by_count":22,"area":"mllm"},{"id":"2405.10305","title":"4D Panoptic Scene Graph Generation","created":"2024-05-16","cited_by_count":22,"area":null},{"id":"2211.13234","title":"RNTrajRec: Road Network Enhanced Trajectory Recovery with Spatial-Temporal Transformer","created":"2022-11-23","cited_by_count":21,"area":null},{"id":"2303.13293","title":"LABRAD-OR: Lightweight Memory Scene Graphs for Accurate Bimodal Reasoning in Dynamic Operating Rooms","created":"2023-03-23","cited_by_count":21,"area":null},{"id":"2207.11441","title":"Meta Spatio-Temporal Debiasing for Video Scene Graph Generation","created":"2022-07-23","cited_by_count":20,"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":"2411.18042","title":"HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation","created":"2024-11-27","cited_by_count":19,"area":"mllm"},{"id":"2501.04336","title":"Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs","created":"2025-01-08","cited_by_count":19,"area":"mllm"},{"id":"2112.05375","title":"Rethinking the Two-Stage Framework for Grounded Situation Recognition","created":"2021-12-10","cited_by_count":16,"area":null},{"id":"2308.05081","title":"Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling","created":"2023-08-09","cited_by_count":15,"area":null},{"id":"2305.08522","title":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs","created":"2023-05-15","cited_by_count":14,"area":null},{"id":"2304.07647","title":"LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision","created":"2023-04-15","cited_by_count":13,"area":null},{"id":"2306.03597","title":"Human-Object Interaction Prediction in Videos through Gaze Following","created":"2023-06-06","cited_by_count":13,"area":null},{"id":"2309.16524","title":"HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTs","created":"2023-09-28","cited_by_count":12,"area":null},{"id":"2205.02958","title":"Scene Graph Expansion for Semantics-Guided Image Outpainting","created":"2022-05-05","cited_by_count":11,"area":null},{"id":"2406.01029","title":"CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2503.13957","title":"DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation","created":"2025-03-18","cited_by_count":11,"area":null},{"id":"2503.15005","title":"Universal Scene Graph Generation","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2309.13237","title":"Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation","created":"2023-09-23","cited_by_count":10,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2403.04899","title":"Towards Scene Graph Anticipation","created":"2024-03-07","cited_by_count":10,"area":null},{"id":"2412.16447","title":"A Generalizable Anomaly Detection Method in Dynamic Graphs","created":"2024-12-21","cited_by_count":10,"area":null},{"id":"2302.03477","title":"Explainable Action Prediction through Self-Supervision on Scene Graphs","created":"2023-02-07","cited_by_count":9,"area":null},{"id":"2211.06119","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","created":"2022-11-11","cited_by_count":8,"area":null},{"id":"2304.04978","title":"StageInteractor: Query-based Object Detector with Cross-stage Interaction","created":"2023-04-11","cited_by_count":8,"area":null},{"id":"2410.17986","title":"Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data","created":"2024-10-23","cited_by_count":8,"area":null},{"id":"2307.00586","title":"ClipSitu: Effectively Leveraging CLIP for Conditional Predictions in Situation Recognition","created":"2023-07-02","cited_by_count":6,"area":null},{"id":"2403.10107","title":"Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning","created":"2024-03-15","cited_by_count":6,"area":"lr"},{"id":"2411.13059","title":"Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation","created":"2024-11-20","cited_by_count":6,"area":null},{"id":"2503.15019","title":"Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2404.07788","title":"AUG: A New Dataset and An Efficient Model for Aerial Image Urban Scene Graph Generation","created":"2024-04-11","cited_by_count":5,"area":null},{"id":"2407.11433","title":"CycleHOI: Improving Human-Object Interaction Detection with Cycle Consistency of Detection and Generation","created":"2024-07-16","cited_by_count":5,"area":"diffusion"},{"id":"2412.11026","title":"SceneLLM: Implicit Language Reasoning in LLM for Dynamic Scene Graph Generation","created":"2024-12-15","cited_by_count":5,"area":"lr"},{"id":"2602.17555","title":"GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking","created":"2026-02-19","cited_by_count":5,"area":"lr"},{"id":"2305.02398","title":"Learning-based Relational Object Matching Across Views","created":"2023-05-03","cited_by_count":4,"area":null},{"id":"2410.22829","title":"Situational Scene Graph for Structured Human-centric Situation Understanding","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2502.15370","title":"Weakly Supervised Video Scene Graph Generation via Natural Language Supervision","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2212.01186","title":"A General Purpose Supervisory Signal for Embodied Agents","created":"2022-12-01","cited_by_count":3,"area":null},{"id":"2301.07666","title":"DDS: Decoupled Dynamic Scene-Graph Generation Network","created":"2023-01-18","cited_by_count":3,"area":null},{"id":"2303.13209","title":"Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learning","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2306.10122","title":"Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2311.12820","title":"MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2409.12499","title":"End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2509.21576","title":"Vision Language Models Cannot Plan, but Can They Formalize?","created":"2025-09-25","cited_by_count":3,"area":"mllm"},{"id":"2602.23543","title":"Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2207.00782","title":"Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2407.20642","title":"Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2509.06165","title":"UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning","created":"2025-09-07","cited_by_count":2,"area":null},{"id":"2604.10397","title":"Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipation","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2604.20136","title":"IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory","created":"2026-04-22","cited_by_count":2,"area":null},{"id":"2605.07575","title":"Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2305.15692","title":"Deep Neural Networks in Video Human Action Recognition: A Review","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2307.16309","title":"Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation","created":"2023-07-30","cited_by_count":1,"area":null},{"id":"2401.12479","title":"TD^2-Net: Toward Denoising and Debiasing for Dynamic Scene Graph Generation","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2505.06663","title":"METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection","created":"2025-05-10","cited_by_count":1,"area":null},{"id":"2506.01487","title":"FDSG: Forecasting Dynamic Scene Graphs","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2509.05661","title":"Language-Driven Object-Oriented Two-Stage Method for Scene Graph Anticipation","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2509.21783","title":"Prompt-guided Disentangled Representation for Action Recognition","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2512.05524","title":"VOST-SGG: VLM-Aided One-Stage Spatio-Temporal Scene Graph Generation","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2603.21559","title":"Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2605.13667","title":"SceneGraphVLM: Dynamic Scene Graph Generation from Video with Vision-Language Models","created":"2026-05-13","cited_by_count":1,"area":"mllm"},{"id":"2607.02425","title":"Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2308.05274","title":"Local-Global Information Interaction Debiasing for Dynamic Scene Graph Generation","created":"2023-08-10","cited_by_count":0,"area":null},{"id":"2309.08179","title":"STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph Generation","created":"2023-09-15","cited_by_count":0,"area":"distill"},{"id":"2310.10879","title":"BLoad: Enhancing Neural Network Training with Efficient Sequential Data Handling","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2409.00295","title":"Box2Flow: Instance-based Action Flow Graphs from Videos","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2410.07987","title":"A transition towards virtual representations of visual scenes","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2503.15846","title":"A Closer Look at Dynamic Scene Graph Generation In the Era of Multimodal Large Language Models","created":"2025-03-20","cited_by_count":0,"area":"mllm"},{"id":"2504.05463","title":"REVEAL: Relation-based Video Representation Learning for Video-Question-Answering","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.22011","title":"Prototype Embedding Optimization for Human-Object Interaction Detection in Livestreaming","created":"2025-05-28","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":"2508.07171","title":"EventRR: Event Referential Reasoning for Referring Video Object Segmentation","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2604.08342","title":"EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.17298","title":"Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.19631","title":"MOSA: Motion-Guided Semantic Alignment for Dynamic Scene Graph Generation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2607.04017","title":"SAGE: Synchronized Action-Gaze Recognition and Anticipation for Human Behavior Understanding","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.21228","title":"T-STAR: A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.26097","title":"Knowledge-guided Disentanglement with Atomic Actions for Action Recognition","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.02056","title":"TBSG-Net: Temporal Bipartite Scene Graph Network for Fine-Grained Video Moment Retrieval","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.14835","title":"OvDSGG: End-to-End Open-Vocabulary Dynamic Scene Graph Generation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2610.20091","title":"RTAformer: Relation-Transition-Aware Transformer for Video Scene Graph Generation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}