{"total":31,"rows":[{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42,"area":null},{"id":"2404.02257","title":"SnAG: Scalable and Accurate Video Grounding","created":"2024-04-02","cited_by_count":36,"area":null},{"id":"2412.06284","title":"Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Data","created":"2024-12-09","cited_by_count":21,"area":null},{"id":"2310.11612","title":"Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks","created":"2023-10-17","cited_by_count":20,"area":null},{"id":"2412.15678","title":"Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2503.12560","title":"Multi-Granular Multimodal Clue Fusion for Meme Understanding","created":"2025-03-16","cited_by_count":14,"area":null},{"id":"2504.02454","title":"Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation","created":"2025-04-03","cited_by_count":14,"area":null},{"id":"2407.13519","title":"GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding","created":"2024-07-18","cited_by_count":12,"area":null},{"id":"2409.09953","title":"Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection","created":"2024-09-16","cited_by_count":12,"area":null},{"id":"2505.04270","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2412.07183","title":"Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2412.15668","title":"Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection","created":"2024-12-20","cited_by_count":8,"area":null},{"id":"2506.17633","title":"Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection","created":"2025-06-21","cited_by_count":8,"area":null},{"id":"2605.26441","title":"Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective","created":"2026-05-26","cited_by_count":8,"area":null},{"id":"2310.06365","title":"Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment","created":"2023-10-10","cited_by_count":7,"area":null},{"id":"2312.09716","title":"Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2406.10079","title":"Localizing Events in Videos with Multimodal Queries","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2605.29812","title":"Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Language","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2412.07157","title":"Multi-Scale Contrastive Learning for Video Temporal Grounding","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2605.29793","title":"Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language","created":"2026-05-28","cited_by_count":5,"area":null},{"id":"2305.04123","title":"Transform-Equivariant Consistency Learning for Temporal Sentence Grounding","created":"2023-05-06","cited_by_count":3,"area":null},{"id":"2404.05083","title":"DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Models","created":"2024-04-07","cited_by_count":3,"area":null},{"id":"2506.05286","title":"Stable Vision Concept Transformers for Medical Diagnosis","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2605.30742","title":"Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2605.30750","title":"SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2412.09044","title":"Motif Guided Graph Transformer with Combinatorial Skeleton Prototype Learning for Skeleton-Based Person Re-Identification","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2412.13510","title":"Dynamic Adapter with Semantics Disentangling for Cross-lingual Cross-modal Retrieval","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2606.31004","title":"Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2508.18148","title":"Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2603.07694","title":"Compressed-Domain-Aware Online Video Super-Resolution","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2606.01615","title":"Turing Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrieval","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}