{"total":32,"rows":[{"id":"2101.06653","title":"LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting","created":"2021-01-17","cited_by_count":113,"area":null},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41,"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":"2107.10234","title":"Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks","created":"2021-07-21","cited_by_count":19,"area":null},{"id":"2109.12776","title":"Joint Multimedia Event Extraction from Video and Article","created":"2021-09-27","cited_by_count":19,"area":null},{"id":"2203.16518","title":"Collaborative Transformers for Grounded Situation Recognition","created":"2022-03-30","cited_by_count":19,"area":null},{"id":"2104.10283","title":"GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering","created":"2021-04-20","cited_by_count":16,"area":null},{"id":"2112.05375","title":"Rethinking the Two-Stage Framework for Grounded Situation Recognition","created":"2021-12-10","cited_by_count":16,"area":null},{"id":"2111.10135","title":"Grounded Situation Recognition with Transformers","created":"2021-11-19","cited_by_count":14,"area":null},{"id":"2105.11866","title":"GraphFM: Graph Factorization Machines for Feature Interaction Modeling","created":"2021-05-25","cited_by_count":13,"area":null},{"id":"2210.10828","title":"Grounded Video Situation Recognition","created":"2022-10-19","cited_by_count":13,"area":null},{"id":"2307.07757","title":"Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments","created":"2023-07-15","cited_by_count":13,"area":null},{"id":"2112.06910","title":"DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points","created":"2021-12-13","cited_by_count":8,"area":null},{"id":"2101.02385","title":"Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting","created":"2021-01-07","cited_by_count":6,"area":null},{"id":"2208.04165","title":"Neural Message Passing for Visual Relationship Detection","created":"2022-08-08","cited_by_count":6,"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":"2108.02365","title":"Hybrid Reasoning Network for Video-based Commonsense Captioning","created":"2021-08-05","cited_by_count":4,"area":null},{"id":"2212.10207","title":"Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2308.10562","title":"Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories","created":"2023-08-21","cited_by_count":4,"area":null},{"id":"2405.00742","title":"Federated Graph Learning for EV Charging Demand Forecasting with Personalization Against Cyberattacks","created":"2024-04-30","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":"2206.07207","title":"Beyond Grounding: Extracting Fine-Grained Event Hierarchies Across Modalities","created":"2022-06-14","cited_by_count":3,"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":"2107.01529","title":"Learning Complex Users' Preferences for Recommender Systems","created":"2021-07-04","cited_by_count":1,"area":null},{"id":"2109.05353","title":"Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network","created":"2021-09-11","cited_by_count":1,"area":null},{"id":"2402.19339","title":"Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2103.15514","title":"Context-aware short-term interest first model for session-based recommendation","created":"2021-03-29","cited_by_count":0,"area":null},{"id":"2201.01837","title":"Frame Shift Prediction","created":"2022-01-05","cited_by_count":0,"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":"2212.02875","title":"Multi-Task Edge Prediction in Temporally-Dynamic Video Graphs","created":"2022-12-06","cited_by_count":0,"area":null},{"id":"2508.21816","title":"The Demon is in Ambiguity: Revisiting Situation Recognition with Single Positive Multi-Label Learning","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2606.26424","title":"Rethinking Training & Inference for Forecasting: Linking Winner-Take-All back to GMMs","created":"2026-06-24","cited_by_count":0,"area":null}],"next_cursor":null}