{"total":88,"rows":[{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2204.03649","title":"Unsupervised Prompt Learning for Vision-Language Models","created":"2022-04-07","cited_by_count":127,"area":"mllm"},{"id":"2309.09812","title":"R2GenGPT: Radiology Report Generation with Frozen LLMs","created":"2023-09-18","cited_by_count":114,"area":null},{"id":"2303.16406","title":"Hierarchical Video-Moment Retrieval and Step-Captioning","created":"2023-03-29","cited_by_count":83,"area":null},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79,"area":null},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72,"area":null},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"area":null},{"id":"2506.01300","title":"ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding","created":"2025-06-02","cited_by_count":50,"area":"agents"},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2411.14517","title":"The Double-Ellipsoid Geometry of CLIP","created":"2024-11-21","cited_by_count":42,"area":null},{"id":"2203.05796","title":"Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision","created":"2022-03-11","cited_by_count":36,"area":null},{"id":"2304.08386","title":"Progressive Visual Prompt Learning with Contrastive Feature Re-formation","created":"2023-04-17","cited_by_count":36,"area":null},{"id":"2310.04900","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","created":"2023-10-07","cited_by_count":34,"area":null},{"id":"2312.03014","title":"Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey","created":"2023-12-05","cited_by_count":34,"area":null},{"id":"2310.16640","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","created":"2023-10-25","cited_by_count":31,"area":null},{"id":"2303.12423","title":"Text with Knowledge Graph Augmented Transformer for Video Captioning","created":"2023-03-22","cited_by_count":28,"area":null},{"id":"2306.09244","title":"Text Promptable Surgical Instrument Segmentation with Vision-Language Models","created":"2023-06-15","cited_by_count":28,"area":"mllm"},{"id":"2206.00629","title":"CLIP4IDC: CLIP for Image Difference Captioning","created":"2022-06-01","cited_by_count":25,"area":null},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25,"area":null},{"id":"2406.00919","title":"Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2303.02344","title":"Improving Audio-Visual Video Parsing with Pseudo Visual Labels","created":"2023-03-04","cited_by_count":18,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2305.13167","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","created":"2023-05-22","cited_by_count":17,"area":null},{"id":"2312.08878","title":"Domain Prompt Learning with Quaternion Networks","created":"2023-12-12","cited_by_count":17,"area":"mllm"},{"id":"2304.10782","title":"Contrastive Language, Action, and State Pre-training for Robot Learning","created":"2023-04-21","cited_by_count":16,"area":null},{"id":"2306.00595","title":"Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2507.22264","title":"SmartCLIP: Modular Vision-language Alignment with Identification Guarantees","created":"2025-07-29","cited_by_count":14,"area":null},{"id":"2503.23388","title":"COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation","created":"2025-03-30","cited_by_count":13,"area":"mllm"},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2311.07514","title":"VGSG: Vision-Guided Semantic-Group Network for Text-based Person Search","created":"2023-11-13","cited_by_count":11,"area":null},{"id":"2308.12045","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","created":"2023-08-23","cited_by_count":10,"area":null},{"id":"2404.13370","title":"Movie101v2: Improved Movie Narration Benchmark","created":"2024-04-20","cited_by_count":9,"area":null},{"id":"2406.13123","title":"ViLCo-Bench: VIdeo Language COntinual learning Benchmark","created":"2024-06-19","cited_by_count":9,"area":null},{"id":"2506.02439","title":"Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2308.11171","title":"ViCo: Engaging Video Comment Generation with Human Preference Rewards","created":"2023-08-22","cited_by_count":8,"area":"alignment"},{"id":"2312.00347","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","created":"2023-12-01","cited_by_count":8,"area":null},{"id":"2501.19061","title":"EgoMe: A New Dataset and Challenge for Following Me via Egocentric View in Real World","created":"2025-01-31","cited_by_count":8,"area":"offlinerl"},{"id":"2305.11439","title":"Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment","created":"2023-05-19","cited_by_count":7,"area":"mllm"},{"id":"2307.03339","title":"Open-Vocabulary Object Detection via Scene Graph Discovery","created":"2023-07-07","cited_by_count":7,"area":null},{"id":"2311.17315","title":"Explaining CLIP's performance disparities on data from blind/low vision users","created":"2023-11-29","cited_by_count":7,"area":"mllm"},{"id":"2409.15196","title":"HOTVCOM: Generating Buzzworthy Comments for Videos","created":"2024-09-23","cited_by_count":7,"area":null},{"id":"2507.20163","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning","created":"2025-07-27","cited_by_count":7,"area":null},{"id":"2403.17556","title":"m3P: Towards Multimodal Multilingual Translation with Multimodal Prompt","created":"2024-03-26","cited_by_count":6,"area":null},{"id":"2403.19603","title":"Semantic Map-based Generation of Navigation Instructions","created":"2024-03-28","cited_by_count":6,"area":null},{"id":"2404.17498","title":"Learning text-to-video retrieval from image captioning","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2409.19526","title":"Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats","created":"2024-09-29","cited_by_count":6,"area":"safety"},{"id":"2207.05526","title":"Long-term Leap Attention, Short-term Periodic Shift for Video Classification","created":"2022-07-12","cited_by_count":5,"area":null},{"id":"2302.09736","title":"STOA-VLP: Spatial-Temporal Modeling of Object and Action for Video-Language Pre-training","created":"2023-02-20","cited_by_count":5,"area":null},{"id":"2307.16399","title":"Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2406.09198","title":"CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2505.10088","title":"MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models","created":"2025-05-15","cited_by_count":4,"area":"mllm"},{"id":"2207.03038","title":"Dual-Stream Transformer for Generic Event Boundary Captioning","created":"2022-07-07","cited_by_count":3,"area":null},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","cited_by_count":3,"area":"lr"},{"id":"2305.08389","title":"Edit As You Wish: Video Caption Editing with Multi-grained User Control","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2306.11341","title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2409.06224","title":"MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2503.17417","title":"Generative Modeling of Class Probability for Multi-Modal Representation Learning","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2506.00835","title":"SynPO: Synergizing Descriptiveness and Preference Optimization for Video Detailed Captioning","created":"2025-06-01","cited_by_count":3,"area":"alignment"},{"id":"2508.07312","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2510.10022","title":"Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning","created":"2025-10-11","cited_by_count":3,"area":null},{"id":"2305.14969","title":"MMNet: Multi-Mask Network for Referring Image Segmentation","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2401.04903","title":"SnapCap: Efficient Snapshot Compressive Video Captioning","created":"2024-01-10","cited_by_count":2,"area":null},{"id":"2401.13888","title":"Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark","created":"2024-01-25","cited_by_count":2,"area":null},{"id":"2510.10671","title":"Image-to-Video Transfer Learning based on Image-Language Foundation Models: A Comprehensive Survey","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2603.04803","title":"Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2209.15000","title":"REST: REtrieve & Self-Train for generative action recognition","created":"2022-09-29","cited_by_count":1,"area":"synth"},{"id":"2310.19554","title":"Harvest Video Foundation Models via Efficient Post-Pretraining","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2311.02699","title":"Nepali Video Captioning using CNN-RNN Architecture","created":"2023-11-05","cited_by_count":1,"area":null},{"id":"2312.15670","title":"Open-Vocabulary Video Relation Extraction","created":"2023-12-25","cited_by_count":1,"area":null},{"id":"2411.01975","title":"SPECTRUM: Semantic Processing and Emotion-informed video-Captioning Through Retrieval and Understanding Modalities","created":"2024-11-04","cited_by_count":1,"area":null},{"id":"2411.14688","title":"Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning","created":"2024-11-22","cited_by_count":1,"area":null},{"id":"2503.17899","title":"What Time Tells Us? An Explorative Study of Time Awareness Learned from Static Images","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2505.12656","title":"SPKLIP: Aligning Spike Video Streams with Natural Language","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2507.06072","title":"MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding","created":"2025-07-08","cited_by_count":1,"area":"driving"},{"id":"2208.11307","title":"Visual Subtitle Feature Enhanced Video Outline Generation","created":"2022-08-24","cited_by_count":0,"area":null},{"id":"2308.12408","title":"An Initial Exploration: Learning to Generate Realistic Audio for Silent Video","created":"2023-08-23","cited_by_count":0,"area":null},{"id":"2408.12141","title":"TRRG: Towards Truthful Radiology Report Generation With Cross-modal Disease Clue Enhanced Large Language Model","created":"2024-08-22","cited_by_count":0,"area":"mllm"},{"id":"2412.13543","title":"Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2502.13754","title":"Capturing Rich Behavior Representations: A Dynamic Action Semantic-Aware Graph Transformer for Video Captioning","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2502.19450","title":"CLIP-Optimized Multimodal Image Enhancement via ISP-CNN Fusion for Coal Mine IoVT under Uneven Illumination","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2506.18544","title":"Normality Prior Guided Multi-Semantic Fusion Network for Unsupervised Image Anomaly Detection","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2512.05385","title":"ShaRP: SHAllow-LayeR Pruning for Efficient Video Large Language Models","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2601.08204","title":"MobiDiary: Autoregressive Action Captioning with Wearable Devices and Wireless Signals","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2606.31187","title":"Learning to Deny: Action Denial in Multimodal Large Language Models","created":"2026-06-30","cited_by_count":0,"area":"mllm"},{"id":"2608.19646","title":"PL-NBA: A Possession-level Universal Basketball Video Dataset Supporting Multiple Visual Understanding Tasks","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.20690","title":"Identity-Aware Human-Object Interaction Motion Captioning","created":"2026-08-21","cited_by_count":0,"area":null}],"next_cursor":null}