{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"1904.02639","title":"Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection","created":"2019-04-04","cited_by_count":564},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"1604.04574","title":"Learning Temporal Regularity in Video Sequences","created":"2016-04-15","cited_by_count":254},{"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":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230},{"id":"1903.07256","title":"Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection","created":"2019-03-18","cited_by_count":171},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138},{"id":"2108.06852","title":"A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction","created":"2021-08-16","cited_by_count":129},{"id":"2203.03962","title":"Generative Cooperative Learning for Unsupervised Video Anomaly Detection","created":"2022-03-08","cited_by_count":102},{"id":"2302.05160","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","created":"2023-02-10","cited_by_count":90},{"id":"2211.15098","title":"MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection","created":"2022-11-28","cited_by_count":89},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67},{"id":"1908.05884","title":"GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection","created":"2019-08-16","cited_by_count":64},{"id":"2303.12369","title":"Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection","created":"2023-03-22","cited_by_count":64},{"id":"2003.06845","title":"SF-Net: Single-Frame Supervision for Temporal Action Localization","created":"2020-03-15","cited_by_count":62},{"id":"2311.07042","title":"Open-Vocabulary Video Anomaly Detection","created":"2023-11-13","cited_by_count":57},{"id":"2304.05112","title":"Video Event Restoration Based on Keyframes for Video Anomaly Detection","created":"2023-04-11","cited_by_count":54},{"id":"2404.08531","title":"Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection","created":"2024-04-12","cited_by_count":49},{"id":"2401.05702","title":"Video Anomaly Detection and Explanation via Large Language Models","created":"2024-01-11","cited_by_count":47},{"id":"2306.14451","title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","created":"2023-06-26","cited_by_count":43},{"id":"2108.05029","title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","created":"2021-08-11","cited_by_count":42},{"id":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41},{"id":"2211.00882","title":"DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network","created":"2022-11-02","cited_by_count":26},{"id":"2304.05841","title":"Exploring Diffusion Models for Unsupervised Video Anomaly Detection","created":"2023-04-12","cited_by_count":23},{"id":"2204.09409","title":"Video Moment Retrieval from Text Queries via Single Frame Annotation","created":"2022-04-20","cited_by_count":19},{"id":"1901.10364","title":"Anomaly Locality in Video Surveillance","created":"2019-01-29","cited_by_count":18},{"id":"1604.07602","title":"Spot On: Action Localization from Pointly-Supervised Proposals","created":"2016-04-26","cited_by_count":17},{"id":"2308.12608","title":"HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation","created":"2023-08-24","cited_by_count":16},{"id":"2310.10125","title":"Few-shot Action Recognition with Captioning Foundation Models","created":"2023-10-16","cited_by_count":9},{"id":"2308.04197","title":"D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation","created":"2023-08-08","cited_by_count":8},{"id":"2403.06154","title":"GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detection","created":"2024-03-10","cited_by_count":7}],"next_cursor":null}