{"total":55,"rows":[{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658,"area":"diffusion"},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61,"area":"mllm"},{"id":"2308.06202","title":"Exploring Predicate Visual Context in Detecting Human-Object Interactions","created":"2023-08-11","cited_by_count":56,"area":null},{"id":"2308.09351","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","created":"2023-08-18","cited_by_count":45,"area":null},{"id":"2404.00986","title":"Make Continual Learning Stronger via C-Flat","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2311.03799","title":"Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models","created":"2023-11-07","cited_by_count":34,"area":null},{"id":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28,"area":null},{"id":"2410.23904","title":"EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection","created":"2024-10-31","cited_by_count":28,"area":null},{"id":"2408.02484","title":"Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection","created":"2024-08-05","cited_by_count":26,"area":null},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25,"area":null},{"id":"2503.07602","title":"DreamRelation: Relation-Centric Video Customization","created":"2025-03-10","cited_by_count":23,"area":null},{"id":"2303.14005","title":"Category Query Learning for Human-Object Interaction Classification","created":"2023-03-24","cited_by_count":21,"area":null},{"id":"2311.03354","title":"CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding","created":"2023-11-06","cited_by_count":20,"area":null},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14,"area":null},{"id":"2303.08998","title":"Unified Visual Relationship Detection with Vision and Language Models","created":"2023-03-16","cited_by_count":13,"area":null},{"id":"2307.13529","title":"Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection","created":"2023-07-25","cited_by_count":13,"area":null},{"id":"2312.05849","title":"InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models","created":"2023-12-10","cited_by_count":13,"area":"diffusion"},{"id":"2505.19503","title":"Locality-Aware Zero-Shot Human-Object Interaction Detection","created":"2025-05-26","cited_by_count":12,"area":"mllm"},{"id":"2507.15542","title":"HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation","created":"2025-07-21","cited_by_count":12,"area":null},{"id":"2308.08529","title":"Diagnosing Human-object Interaction Detectors","created":"2023-08-16","cited_by_count":11,"area":null},{"id":"2310.10125","title":"Few-shot Action Recognition with Captioning Foundation Models","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2501.01045","title":"ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2211.15215","title":"Progressive Learning without Forgetting","created":"2022-11-28","cited_by_count":7,"area":null},{"id":"2403.14270","title":"Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection","created":"2024-03-21","cited_by_count":6,"area":null},{"id":"2407.21438","title":"A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap","created":"2024-07-31","cited_by_count":6,"area":null},{"id":"2506.07643","title":"Synthetic Visual Genome","created":"2025-06-09","cited_by_count":6,"area":null},{"id":"2503.18134","title":"An Image-like Diffusion Method for Human-Object Interaction Detection","created":"2025-03-23","cited_by_count":5,"area":null},{"id":"2508.18753","title":"CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methods","created":"2025-08-26","cited_by_count":5,"area":"mllm"},{"id":"2307.02291","title":"Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor","created":"2023-07-05","cited_by_count":4,"area":"mllm"},{"id":"2403.07246","title":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration","created":"2024-03-12","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":"2304.00590","title":"SPAN: Learning Similarity between Scene Graphs and Images with Transformers","created":"2023-04-02","cited_by_count":3,"area":null},{"id":"2311.16475","title":"Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models","created":"2023-11-26","cited_by_count":3,"area":"mllm"},{"id":"2508.04943","title":"TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring","created":"2025-08-07","cited_by_count":3,"area":null},{"id":"2509.00760","title":"No More Sibling Rivalry: Debiasing Human-Object Interaction Detection","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2408.08305","title":"Towards Flexible Visual Relationship Segmentation","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2305.09948","title":"HICO-DET-SG and V-COCO-SG: New Data Splits for Evaluating the Systematic Generalization Performance of Human-Object Interaction Detection Models","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2408.05772","title":"An analysis of HOI: using a training-free method with multimodal visual foundation models when only the test set is available, without the training set","created":"2024-08-11","cited_by_count":1,"area":null},{"id":"2411.18038","title":"VLM-HOI: Vision Language Models for Interpretable Human-Object Interaction Analysis","created":"2024-11-27","cited_by_count":1,"area":"mllm"},{"id":"2501.11653","title":"Dynamic Scene Understanding from Vision-Language Representations","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2508.18860","title":"C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2508.18896","title":"DQEN: Dual Query Enhancement Network for DETR-based HOI Detection","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2511.18811","title":"Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2602.15124","title":"Zero-shot HOI Detection with MLLM-based Detector-agnostic Interaction Recognition","created":"2026-02-16","cited_by_count":1,"area":"mllm"},{"id":"2609.23431","title":"HOIBlender: Blending Lightweight Detection with Vision-Language Priors for Efficient Human-Object Interaction Detection","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2305.00620","title":"Refined Response Distillation for Class-Incremental Player Detection","created":"2023-05-01","cited_by_count":0,"area":null},{"id":"2307.10499","title":"Mining Conditional Part Semantics with Occluded Extrapolation for Human-Object Interaction Detection","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2404.12678","title":"Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model","created":"2024-04-19","cited_by_count":0,"area":"mllm"},{"id":"2501.13584","title":"Towards Robust Incremental Learning under Ambiguous Supervision","created":"2025-01-23","cited_by_count":0,"area":null},{"id":"2507.10977","title":"Conceptualizing Multi-scale Wavelet Attention and Ray-based Encoding for Human-Object Interaction Detection","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2510.27020","title":"Incremental Human-Object Interaction Detection with Invariant Relation Representation Learning","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2512.17640","title":"Generative Human-Object Interaction Detection via Differentiable Cognitive Steering of Multi-modal LLMs","created":"2025-12-19","cited_by_count":0,"area":"mllm"},{"id":"2604.00507","title":"RegFormer: Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2610.18161","title":"Benchmarking Multimodal Large Language Models for Zero-Shot Human-Object Interaction","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}