{"list":"other","total":53,"rows":[{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2108.07610","title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","created":"2021-08-17","cited_by_count":514},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2003.13228","title":"Learning Memory-guided Normality for Anomaly Detection","created":"2020-03-30","cited_by_count":278},{"id":"2310.18961","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","created":"2023-10-29","cited_by_count":271},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"2303.15140","title":"SimpleNet: A Simple Network for Image Anomaly Detection and Localization","created":"2023-03-27","cited_by_count":256},{"id":"1604.04574","title":"Learning Temporal Regularity in Video Sequences","created":"2016-04-15","cited_by_count":254},{"id":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230},{"id":"2406.02918","title":"U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation","created":"2024-06-05","cited_by_count":179},{"id":"2011.07491","title":"Anomaly Detection in Video via Self-Supervised and Multi-Task Learning","created":"2020-11-15","cited_by_count":148},{"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":"2407.15795","title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","created":"2024-07-22","cited_by_count":127},{"id":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123},{"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":"2305.11003","title":"Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping","created":"2023-05-18","cited_by_count":92},{"id":"1902.05872","title":"Street Scene: A new dataset and evaluation protocol for video anomaly detection","created":"2019-02-15","cited_by_count":90},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"id":"2008.12328","title":"A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video","created":"2020-08-27","cited_by_count":86},{"id":"2406.11138","title":"Diffusion Models in Low-Level Vision: A Survey","created":"2024-06-17","cited_by_count":74},{"id":"2008.11988","title":"Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events","created":"2020-08-27","cited_by_count":70},{"id":"2311.11638","title":"Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model","created":"2023-11-20","cited_by_count":69},{"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":"2305.15956","title":"Anomaly Detection with Conditioned Denoising Diffusion Models","created":"2023-05-25","cited_by_count":56},{"id":"2308.03166","title":"Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects","created":"2023-08-06","cited_by_count":56},{"id":"2410.08261","title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","created":"2024-10-10","cited_by_count":56},{"id":"1709.09121","title":"Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge","created":"2017-09-26","cited_by_count":55},{"id":"2004.07941","title":"Continual Learning for Anomaly Detection in Surveillance Videos","created":"2020-04-15","cited_by_count":49},{"id":"2012.05440","title":"Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding","created":"2020-12-10","cited_by_count":48},{"id":"2303.10326","title":"Diff-UNet: A Diffusion Embedded Network for Volumetric Segmentation","created":"2023-03-18","cited_by_count":41},{"id":"2408.14562","title":"A Survey of Camouflaged Object Detection and Beyond","created":"2024-08-26","cited_by_count":37},{"id":"2004.02072","title":"Any-Shot Sequential Anomaly Detection in Surveillance Videos","created":"2020-04-05","cited_by_count":34},{"id":"2208.14876","title":"NestedFormer: Nested Modality-Aware Transformer for Brain Tumor Segmentation","created":"2022-08-31","cited_by_count":34},{"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":"2412.04280","title":"HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing","created":"2024-12-05","cited_by_count":29},{"id":"2501.18783","title":"RUN: Reversible Unfolding Network for Concealed Object Segmentation","created":"2025-01-30","cited_by_count":28},{"id":"2409.08500","title":"Cross-conditioned Diffusion Model for Medical Image to Image Translation","created":"2024-09-13","cited_by_count":26},{"id":"2108.11168","title":"Adversarially Robust One-class Novelty Detection","created":"2021-08-25","cited_by_count":24},{"id":"2403.14497","title":"MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection","created":"2024-03-21","cited_by_count":22},{"id":"2310.16002","title":"Integrating View Conditions for Image Synthesis","created":"2023-10-24","cited_by_count":16},{"id":"2407.14900","title":"AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement","created":"2024-07-20","cited_by_count":16},{"id":"2103.09097","title":"Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification","created":"2021-03-16","cited_by_count":15},{"id":"2105.14732","title":"Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation","created":"2021-05-31","cited_by_count":15},{"id":"2009.05722","title":"Generator Versus Segmentor: Pseudo-healthy Synthesis","created":"2020-09-12","cited_by_count":12},{"id":"2103.09094","title":"Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation","created":"2021-03-16","cited_by_count":11},{"id":"2409.16225","title":"VideoPatchCore: An Effective Method to Memorize Normality for Video Anomaly Detection","created":"2024-09-24","cited_by_count":8},{"id":"2210.15741","title":"Spatio-temporal predictive tasks for abnormal event detection in videos","created":"2022-10-27","cited_by_count":3}],"next_cursor":null}