{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"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":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"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":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"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":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"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":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300},{"id":"2003.13228","title":"Learning Memory-guided Normality for Anomaly Detection","created":"2020-03-30","cited_by_count":278},{"id":"1604.04574","title":"Learning Temporal Regularity in Video Sequences","created":"2016-04-15","cited_by_count":254},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","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":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234},{"id":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187},{"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":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123},{"id":"1908.06351","title":"Anomaly Detection in Video Sequence with Appearance-Motion Correspondence","created":"2019-08-17","cited_by_count":118},{"id":"1812.04960","title":"Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video","created":"2018-12-11","cited_by_count":111},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107},{"id":"2204.14095","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","created":"2022-04-29","cited_by_count":104},{"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":"2011.12077","title":"CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection","created":"2020-11-24","cited_by_count":79},{"id":"2412.06171","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","created":"2024-12-09","cited_by_count":70},{"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":"2007.07843","title":"Few-shot Scene-adaptive Anomaly Detection","created":"2020-07-15","cited_by_count":62},{"id":"2407.10299","title":"Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models","created":"2024-07-14","cited_by_count":57},{"id":"2404.08531","title":"Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection","created":"2024-04-12","cited_by_count":49},{"id":"1907.10211","title":"Motion-Aware Feature for Improved Video Anomaly Detection","created":"2019-07-24","cited_by_count":48},{"id":"2405.00181","title":"Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly","created":"2024-04-30","cited_by_count":45},{"id":"2104.07268","title":"Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning","created":"2021-04-15","cited_by_count":44},{"id":"2108.03825","title":"Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video","created":"2021-08-09","cited_by_count":32},{"id":"2001.09189","title":"Learning a distance function with a Siamese network to localize anomalies in videos","created":"2020-01-24","cited_by_count":31},{"id":"2001.06812","title":"GTNet: Generative Transfer Network for Zero-Shot Object Detection","created":"2020-01-19","cited_by_count":25},{"id":"2307.09316","title":"MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds","created":"2023-07-18","cited_by_count":19},{"id":"2008.06963","title":"Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians","created":"2020-08-16","cited_by_count":17},{"id":"2506.01701","title":"Data Pruning by Information Maximization","created":"2025-06-02","cited_by_count":15},{"id":"2210.05593","title":"Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection","created":"2022-10-11","cited_by_count":14},{"id":"2104.14770","title":"Cleaning Label Noise with Clusters for Minimally Supervised Anomaly Detection","created":"2021-04-30","cited_by_count":13},{"id":"2403.19314","title":"Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction","created":"2024-03-28","cited_by_count":12},{"id":"2409.05162","title":"Can OOD Object Detectors Learn from Foundation Models?","created":"2024-09-08","cited_by_count":10},{"id":"2410.15980","title":"Learning from Neighbors: Category Extrapolation for Long-Tail Learning","created":"2024-10-21","cited_by_count":9},{"id":"2009.05250","title":"Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification","created":"2020-09-11","cited_by_count":1}],"next_cursor":null}