{"total":49,"rows":[{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062,"area":null},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857,"area":null},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497,"area":null},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309,"area":null},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234,"area":null},{"id":"2410.15458","title":"Allegro: Open the Black Box of Commercial-Level Video Generation Model","created":"2024-10-20","cited_by_count":70,"area":null},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67,"area":null},{"id":"2405.16886","title":"Hawk: Learning to Understand Open-World Video Anomalies","created":"2024-05-27","cited_by_count":49,"area":null},{"id":"2411.13503","title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","created":"2024-11-20","cited_by_count":45,"area":null},{"id":"2410.00741","title":"VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models","created":"2024-10-01","cited_by_count":41,"area":null},{"id":"2404.02790","title":"MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation","created":"2024-04-03","cited_by_count":38,"area":null},{"id":"2312.00834","title":"AV-RIR: Audio-Visual Room Impulse Response Estimation","created":"2023-11-30","cited_by_count":20,"area":null},{"id":"2410.05963","title":"Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts","created":"2024-10-08","cited_by_count":16,"area":null},{"id":"2401.17910","title":"ControlCap: Controllable Region-level Captioning","created":"2024-01-31","cited_by_count":13,"area":null},{"id":"2406.18115","title":"Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps","created":"2024-06-26","cited_by_count":13,"area":null},{"id":"2312.02142","title":"Object Recognition as Next Token Prediction","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2510.02994","title":"Towards Scalable and Consistent 3D Editing","created":"2025-10-03","cited_by_count":10,"area":null},{"id":"2310.00164","title":"PRIME: Prioritizing Interpretability in Failure Mode Extraction","created":"2023-09-29","cited_by_count":9,"area":null},{"id":"2503.18065","title":"Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation","created":"2025-03-23","cited_by_count":8,"area":null},{"id":"2503.18559","title":"AMD-Hummingbird: Towards an Efficient Text-to-Video Model","created":"2025-03-24","cited_by_count":8,"area":null},{"id":"2405.15580","title":"Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2407.11211","title":"Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2506.01950","title":"DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2403.07687","title":"Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2512.14480","title":"SuperCLIP: CLIP with Simple Classification Supervision","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2312.05349","title":"PixLore: A Dataset-driven Approach to Rich Image Captioning","created":"2023-12-08","cited_by_count":3,"area":null},{"id":"2405.16071","title":"DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2411.17767","title":"Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2411.19106","title":"Detailed Object Description with Controllable Dimensions","created":"2024-11-28","cited_by_count":3,"area":null},{"id":"2401.17881","title":"PVLR: Prompt-driven Visual-Linguistic Representation Learning for Multi-Label Image Recognition","created":"2024-01-31","cited_by_count":2,"area":null},{"id":"2407.20920","title":"SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2501.15326","title":"Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data","created":"2025-01-25","cited_by_count":2,"area":null},{"id":"2503.13617","title":"Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2405.02162","title":"Mapping the Unseen: Unified Promptable Panoptic Mapping with Dynamic Labeling using Foundation Models","created":"2024-05-03","cited_by_count":1,"area":null},{"id":"2503.22171","title":"An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval","created":"2025-03-28","cited_by_count":1,"area":null},{"id":"2504.01591","title":"Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2508.21451","title":"MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2603.25767","title":"Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.28450","title":"BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.16807","title":"Connecting Speech to Words through Images","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2412.13614","title":"Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2505.21912","title":"Detecting Cultural Differences in News Video Thumbnails via Computational Aesthetics","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2510.07976","title":"The impact of abstract and object tags on image privacy classification","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2601.12079","title":"EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2607.00839","title":"Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlook","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.24845","title":"LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.26925","title":"Mapping Written Words to Spoken Words in a Different Language Using Only Visual Grounding","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.19592","title":"Selective Cotton Boll Localization for Robotic Harvesting: Evaluation of Deep Learning Vision Models Under Field Conditions","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}