{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"1711.00117","title":"Countering Adversarial Images using Input Transformations","created":"2017-10-31","cited_by_count":520},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"1712.09665","title":"Adversarial Patch","created":"2017-12-27","cited_by_count":517},{"id":"2205.07460","title":"Diffusion Models for Adversarial Purification","created":"2022-05-16","cited_by_count":476},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"1711.01991","title":"Mitigating Adversarial Effects Through Randomization","created":"2017-11-06","cited_by_count":383},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2007.04687","title":"Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision","created":"2020-07-09","cited_by_count":238},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"id":"2502.21271","title":"Adaptive Keyframe Sampling for Long Video Understanding","created":"2025-02-28","cited_by_count":167},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2402.12336","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","created":"2024-02-19","cited_by_count":120},{"id":"1801.02608","title":"LaVAN: Localized and Visible Adversarial Noise","created":"2018-01-08","cited_by_count":113},{"id":"1811.12673","title":"ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples","created":"2018-11-30","cited_by_count":105},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91},{"id":"2412.10360","title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models","created":"2024-12-13","cited_by_count":89},{"id":"2502.19680","title":"M-LLM Based Video Frame Selection for Efficient Video Understanding","created":"2025-02-27","cited_by_count":88},{"id":"1807.01216","title":"Local Gradients Smoothing: Defense against localized adversarial attacks","created":"2018-07-03","cited_by_count":87},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74},{"id":"1801.08926","title":"Deflecting Adversarial Attacks with Pixel Deflection","created":"2018-01-26","cited_by_count":71},{"id":"2112.04532","title":"Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection","created":"2021-12-08","cited_by_count":67},{"id":"1901.01677","title":"Image Super-Resolution as a Defense Against Adversarial Attacks","created":"2019-01-07","cited_by_count":65},{"id":"2108.09135","title":"PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier","created":"2021-08-20","cited_by_count":65},{"id":"2504.02438","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","created":"2025-04-03","cited_by_count":37},{"id":"2404.16452","title":"PAD: Patch-Agnostic Defense against Adversarial Patch Attacks","created":"2024-04-25","cited_by_count":32},{"id":"2410.20971","title":"BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks","created":"2024-10-28","cited_by_count":28},{"id":"2504.17447","title":"FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding","created":"2025-04-24","cited_by_count":27},{"id":"2407.21659","title":"Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models","created":"2024-07-31","cited_by_count":25},{"id":"2409.07353","title":"Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks","created":"2024-09-11","cited_by_count":15},{"id":"2412.01798","title":"SEAL: Semantic Attention Learning for Long Video Representation","created":"2024-12-02","cited_by_count":13},{"id":"1612.08712","title":"Semantic Perceptual Image Compression using Deep Convolution Networks","created":"2016-12-27","cited_by_count":12},{"id":"1902.03771","title":"Pornographic Image Recognition via Weighted Multiple Instance Learning","created":"2019-02-11","cited_by_count":5},{"id":"2412.12833","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","created":"2024-12-17","cited_by_count":5},{"id":"2501.14999","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","created":"2025-01-25","cited_by_count":5},{"id":"2508.10974","title":"Failures to Surface Harmful Contents in Video Large Language Models","created":"2025-08-14","cited_by_count":5},{"id":"2410.03038","title":"CPFD: Confidence-aware Privileged Feature Distillation for Short Video Classification","created":"2024-10-03","cited_by_count":4},{"id":"2509.20851","title":"Poisoning Prompt-Guided Sampling in Video Large Language Models","created":"2025-09-25","cited_by_count":4},{"id":"2505.04488","title":"\"I Can See Forever!\": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments","created":"2025-05-07","cited_by_count":3},{"id":"2410.04449","title":"Video Summarization Techniques: A Comprehensive Review","created":"2024-10-06","cited_by_count":1},{"id":"2510.04245","title":"Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks","created":"2025-10-05","cited_by_count":1}],"next_cursor":null}