{"list":"other","total":58,"rows":[{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"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":"1912.00049","title":"Square Attack: a query-efficient black-box adversarial attack via random search","created":"2019-11-29","cited_by_count":685},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"id":"1710.08864","title":"One pixel attack for fooling deep neural networks","created":"2017-10-24","cited_by_count":582},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"1804.08598","title":"Black-box Adversarial Attacks with Limited Queries and Information","created":"2018-04-23","cited_by_count":501},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"1905.07121","title":"Simple Black-box Adversarial Attacks","created":"2019-05-17","cited_by_count":251},{"id":"2409.14485","title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding","created":"2024-09-22","cited_by_count":213},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"1512.01274","title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","created":"2015-12-03","cited_by_count":195},{"id":"1905.00780","title":"Full-Gradient Representation for Neural Network Visualization","created":"2019-05-02","cited_by_count":191},{"id":"2502.21271","title":"Adaptive Keyframe Sampling for Long Video Understanding","created":"2025-02-28","cited_by_count":167},{"id":"1611.07450","title":"Grad-CAM: Why did you say that?","created":"2016-11-22","cited_by_count":161},{"id":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"1908.02486","title":"STM: SpatioTemporal and Motion Encoding for Action Recognition","created":"2019-08-07","cited_by_count":142},{"id":"1807.04457","title":"Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach","created":"2018-07-12","cited_by_count":130},{"id":"2401.11170","title":"Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images","created":"2024-01-20","cited_by_count":69},{"id":"2004.05682","title":"PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning","created":"2020-04-12","cited_by_count":67},{"id":"2006.12834","title":"Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks","created":"2020-06-23","cited_by_count":65},{"id":"1803.02536","title":"Sparse Adversarial Perturbations for Videos","created":"2018-03-07","cited_by_count":57},{"id":"2008.01919","title":"Adv-watermark: A Novel Watermark Perturbation for Adversarial Examples","created":"2020-08-05","cited_by_count":56},{"id":"1708.04538","title":"Artistic style transfer for videos and spherical images","created":"2017-08-13","cited_by_count":45},{"id":"2411.15720","title":"Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks","created":"2024-11-24","cited_by_count":39},{"id":"2002.05123","title":"Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks","created":"2020-02-12","cited_by_count":36},{"id":"2110.01823","title":"Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations","created":"2021-10-05","cited_by_count":28},{"id":"2411.13136","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","created":"2024-11-20","cited_by_count":23},{"id":"2203.16000","title":"StyleFool: Fooling Video Classification Systems via Style Transfer","created":"2022-03-30","cited_by_count":20},{"id":"2110.15629","title":"Attacking Video Recognition Models with Bullet-Screen Comments","created":"2021-10-29","cited_by_count":16},{"id":"2501.15269","title":"Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink","created":"2025-01-25","cited_by_count":15},{"id":"2403.13507","title":"FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs","created":"2024-03-20","cited_by_count":14},{"id":"2108.13872","title":"Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models","created":"2021-08-29","cited_by_count":12},{"id":"2508.03696","title":"PLA: Prompt Learning Attack against Text-to-Image Generative Models","created":"2025-07-14","cited_by_count":9},{"id":"2402.17533","title":"Black-box Adversarial Attacks Against Image Quality Assessment Models","created":"2024-02-27","cited_by_count":8},{"id":"2112.07921","title":"Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks","created":"2021-12-15","cited_by_count":7},{"id":"2302.14267","title":"Adversarial Attack with Raindrops","created":"2023-02-28","cited_by_count":7},{"id":"2312.09935","title":"LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer","created":"2023-12-15","cited_by_count":7},{"id":"2407.02411","title":"Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs","created":"2024-07-02","cited_by_count":7},{"id":"2508.10974","title":"Failures to Surface Harmful Contents in Video Large Language Models","created":"2025-08-14","cited_by_count":5},{"id":"2411.15555","title":"Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation","created":"2024-11-23","cited_by_count":4},{"id":"2412.09910","title":"Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images","created":"2024-12-13","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":"2408.12099","title":"Query-Efficient Video Adversarial Attack with Stylized Logo on Service Computing","created":"2024-08-22","cited_by_count":3},{"id":"2504.01228","title":"TenAd: A Tensor-based Low-rank Black Box Adversarial Attack for Video Classification","created":"2025-04-01","cited_by_count":1},{"id":"2510.00769","title":"ZQBA: Zero Query Black-box Adversarial Attack","created":"2025-10-01","cited_by_count":1}],"next_cursor":null}