{"total":38,"rows":[{"id":"2103.15538","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","created":"2021-03-29","cited_by_count":84,"area":null},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73,"area":null},{"id":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52,"area":null},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"area":null},{"id":"2203.17251","title":"Continuous Scene Representations for Embodied AI","created":"2022-03-31","cited_by_count":39,"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":"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":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"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":"2207.11441","title":"Meta Spatio-Temporal Debiasing for Video Scene Graph Generation","created":"2022-07-23","cited_by_count":20,"area":null},{"id":"2108.08363","title":"Social Fabric: Tubelet Compositions for Video Relation Detection","created":"2021-08-18","cited_by_count":18,"area":null},{"id":"2108.08669","title":"Video Relation Detection via Tracklet based Visual Transformer","created":"2021-08-19","cited_by_count":17,"area":null},{"id":"2109.13499","title":"Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning","created":"2021-09-28","cited_by_count":16,"area":null},{"id":"2205.10706","title":"GL-RG: Global-Local Representation Granularity for Video Captioning","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2404.04565","title":"SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos","created":"2024-04-06","cited_by_count":15,"area":null},{"id":"2108.08633","title":"Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition","created":"2021-08-19","cited_by_count":12,"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":"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":"2101.08165","title":"Video Relation Detection with Trajectory-aware Multi-modal Features","created":"2021-01-20","cited_by_count":8,"area":null},{"id":"2110.03562","title":"Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2211.07501","title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2310.16073","title":"FloCoDe: Unbiased Dynamic Scene Graph Generation with Temporal Consistency and Correlation Debiasing","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2103.10502","title":"Ano-Graph: Learning Normal Scene Contextual Graphs to Detect Video Anomalies","created":"2021-03-18","cited_by_count":4,"area":null},{"id":"2110.13110","title":"Diagnosing Errors in Video Relation Detectors","created":"2021-10-25","cited_by_count":4,"area":null},{"id":"2307.08984","title":"In Defense of Clip-based Video Relation Detection","created":"2023-07-18","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":"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":"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":"2107.07154","title":"What and When to Look?: Temporal Span Proposal Network for Video Relation Detection","created":"2021-07-15","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":"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":"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":"2410.07987","title":"A transition towards virtual representations of visual scenes","created":"2024-10-10","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}],"next_cursor":null}