{"list":"other","total":64,"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":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"2403.18814","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","created":"2024-03-27","cited_by_count":365},{"id":"2301.04856","title":"Multimodal Deep Learning","created":"2023-01-12","cited_by_count":258},{"id":"1801.10202","title":"The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception","created":"2018-01-30","cited_by_count":254},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247},{"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":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"1904.08298","title":"Events-to-Video: Bringing Modern Computer Vision to Event Cameras","created":"2019-04-17","cited_by_count":193},{"id":"2011.07491","title":"Anomaly Detection in Video via Self-Supervised and Multi-Task Learning","created":"2020-11-15","cited_by_count":148},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138},{"id":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123},{"id":"2207.10022","title":"Secrets of Event-Based Optical Flow","created":"2022-07-20","cited_by_count":92},{"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":"2302.08890","title":"Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks","created":"2023-02-17","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":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85},{"id":"2102.12108","title":"The Promises and Pitfalls of Deep Kernel Learning","created":"2021-02-24","cited_by_count":81},{"id":"2202.02703","title":"Multi-modal Sensor Fusion for Auto Driving Perception: A Survey","created":"2022-02-06","cited_by_count":76},{"id":"2412.06171","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","created":"2024-12-09","cited_by_count":70},{"id":"2408.13627","title":"Recent Event Camera Innovations: A Survey","created":"2024-08-24","cited_by_count":68},{"id":"2303.12369","title":"Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection","created":"2023-03-22","cited_by_count":64},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58},{"id":"2311.07042","title":"Open-Vocabulary Video Anomaly Detection","created":"2023-11-13","cited_by_count":57},{"id":"2301.01928","title":"Event Camera Data Pre-training","created":"2023-01-05","cited_by_count":50},{"id":"2402.04857","title":"Advancing Video Anomaly Detection: A Concise Review and a New Dataset","created":"2024-02-07","cited_by_count":49},{"id":"2405.16886","title":"Hawk: Learning to Understand Open-World Video Anomalies","created":"2024-05-27","cited_by_count":49},{"id":"1605.07148","title":"Backprop KF: Learning Discriminative Deterministic State Estimators","created":"2016-05-23","cited_by_count":47},{"id":"2307.07205","title":"Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","created":"2023-07-14","cited_by_count":42},{"id":"2408.05905","title":"Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts","created":"2024-08-12","cited_by_count":40},{"id":"2306.06354","title":"EventCLIP: Adapting CLIP for Event-based Object Recognition","created":"2023-06-10","cited_by_count":36},{"id":"2308.03135","title":"EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding","created":"2023-08-06","cited_by_count":34},{"id":"2108.03825","title":"Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video","created":"2021-08-09","cited_by_count":32},{"id":"2107.13720","title":"Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection","created":"2021-07-29","cited_by_count":31},{"id":"2311.05152","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","created":"2023-11-09","cited_by_count":31},{"id":"2110.09768","title":"Synthetic Temporal Anomaly Guided End-to-End Video Anomaly Detection","created":"2021-10-19","cited_by_count":26},{"id":"2205.06126","title":"One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code","created":"2022-05-12","cited_by_count":26},{"id":"2303.11011","title":"Learning Optical Flow from Event Camera with Rendered Dataset","created":"2023-03-20","cited_by_count":26},{"id":"2202.05054","title":"Exploiting Spatial Sparsity for Event Cameras with Visual Transformers","created":"2022-02-10","cited_by_count":23},{"id":"2408.12763","title":"Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models","created":"2024-08-22","cited_by_count":23},{"id":"2410.01506","title":"Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion","created":"2024-10-02","cited_by_count":23},{"id":"2012.08637","title":"Multi-Modal Anomaly Detection for Unstructured and Uncertain Environments","created":"2020-12-15","cited_by_count":11},{"id":"2412.20455","title":"Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection","created":"2024-12-29","cited_by_count":10},{"id":"2502.04247","title":"Student-t processes as infinite-width limits of posterior Bayesian neural networks","created":"2025-02-06","cited_by_count":3},{"id":"2310.08315","title":"Fusion framework and multimodality for the Laplacian approximation of Bayesian neural networks","created":"2023-10-12","cited_by_count":2},{"id":"2412.03093","title":"Expanding Event Modality Applications through a Robust CLIP-Based Encoder","created":"2024-12-04","cited_by_count":1}],"next_cursor":null}