{"total":13,"rows":[{"id":"2103.05568","title":"Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering","created":"2021-03-09","cited_by_count":33,"area":null},{"id":"2105.11731","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","created":"2021-05-25","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":"2206.01908","title":"Video-based Human-Object Interaction Detection from Tubelet Tokens","created":"2022-06-04","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":"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":"2407.00917","title":"From Category to Scenery: An End-to-End Framework for Multi-Person Human-Object Interaction Recognition in Videos","created":"2024-07-01","cited_by_count":4,"area":null},{"id":"2512.09646","title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","created":"2025-12-10","cited_by_count":4,"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":"2605.01666","title":"IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction","created":"2026-05-03","cited_by_count":2,"area":null},{"id":"2112.09448","title":"Distillation of Human-Object Interaction Contexts for Action Recognition","created":"2021-12-17","cited_by_count":1,"area":null},{"id":"2206.03061","title":"Spatial Parsing and Dynamic Temporal Pooling networks for Human-Object Interaction detection","created":"2022-06-07","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}],"next_cursor":null}