{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2303.14968","title":"Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective","created":"2023-03-27","cited_by_count":280},{"id":"2207.02595","title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","created":"2022-07-06","cited_by_count":179},{"id":"1908.00375","title":"Quality Assessment of In-the-Wild Videos","created":"2019-08-01","cited_by_count":164},{"id":"2011.13544","title":"Patch-VQ: 'Patching Up' the Video Quality Problem","created":"2020-11-27","cited_by_count":147},{"id":"2207.03482","title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","created":"2022-07-07","cited_by_count":146},{"id":"2005.14354","title":"UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content","created":"2020-05-29","cited_by_count":140},{"id":"2204.14047","title":"A Deep Learning based No-reference Quality Assessment Model for UGC Videos","created":"2022-04-29","cited_by_count":129},{"id":"2108.02818","title":"Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications","created":"2021-08-05","cited_by_count":128},{"id":"1803.01761","title":"Large-Scale Study of Perceptual Video Quality","created":"2018-03-05","cited_by_count":127},{"id":"1904.06457","title":"YouTube UGC Dataset for Video Compression Research","created":"2019-04-13","cited_by_count":124},{"id":"2101.10955","title":"RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content","created":"2021-01-26","cited_by_count":100},{"id":"2108.08505","title":"Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception","created":"2021-08-19","cited_by_count":97},{"id":"2304.00451","title":"Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild","created":"2023-04-02","cited_by_count":97},{"id":"2110.13266","title":"Image Quality Assessment using Contrastive Learning","created":"2021-10-25","cited_by_count":95},{"id":"2003.01966","title":"Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement","created":"2020-03-04","cited_by_count":90},{"id":"2210.10276","title":"CLIP-Driven Fine-grained Text-Image Person Re-identification","created":"2022-10-19","cited_by_count":79},{"id":"2303.13440","title":"CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not","created":"2023-03-23","cited_by_count":79},{"id":"2011.04263","title":"Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training","created":"2020-11-09","cited_by_count":72},{"id":"2309.13625","title":"GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph","created":"2023-09-24","cited_by_count":69},{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68},{"id":"2208.07463","title":"Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets","created":"2022-08-15","cited_by_count":62},{"id":"2111.11591","title":"Efficient Video Transformers with Spatial-Temporal Token Selection","created":"2021-11-23","cited_by_count":59},{"id":"2012.13936","title":"Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessment","created":"2020-12-27","cited_by_count":50},{"id":"2303.14933","title":"MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos","created":"2023-03-27","cited_by_count":46},{"id":"2305.12726","title":"Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach","created":"2023-05-22","cited_by_count":45},{"id":"2103.07666","title":"GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment","created":"2021-03-13","cited_by_count":43},{"id":"2206.09853","title":"DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment","created":"2022-06-20","cited_by_count":41},{"id":"2207.03723","title":"Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment","created":"2022-07-08","cited_by_count":25},{"id":"2304.06440","title":"Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessment","created":"2023-04-13","cited_by_count":21},{"id":"2108.00406","title":"Discovering Distinctive \"Semantics\" in Super-Resolution Networks","created":"2021-08-01","cited_by_count":20},{"id":"2308.00729","title":"Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment","created":"2023-08-01","cited_by_count":20},{"id":"1908.11517","title":"UGC-VIDEO: perceptual quality assessment of user-generated videos","created":"2019-08-30","cited_by_count":19},{"id":"2307.16813","title":"Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment","created":"2023-07-31","cited_by_count":18},{"id":"2108.09635","title":"StarVQA: Space-Time Attention for Video Quality Assessment","created":"2021-08-22","cited_by_count":15},{"id":"2205.04264","title":"SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment","created":"2022-05-09","cited_by_count":14},{"id":"2112.13309","title":"Learning Cross-Scale Weighted Prediction for Efficient Neural Video Compression","created":"2021-12-26","cited_by_count":13},{"id":"2205.10937","title":"muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems","created":"2022-05-22","cited_by_count":12},{"id":"2309.13609","title":"Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks","created":"2023-09-24","cited_by_count":12},{"id":"2304.10091","title":"Learning CLIP Guided Visual-Text Fusion Transformer for Video-based Pedestrian Attribute Recognition","created":"2023-04-20","cited_by_count":10},{"id":"2207.08124","title":"Source-free Unsupervised Domain Adaptation for Blind Image Quality Assessment","created":"2022-07-17","cited_by_count":9},{"id":"2207.06177","title":"RTN: Reinforced Transformer Network for Coronary CT Angiography Vessel-level Image Quality Assessment","created":"2022-07-13","cited_by_count":8},{"id":"2309.17014","title":"FreqAlign: Excavating Perception-oriented Transferability for Blind Image Quality Assessment from A Frequency Perspective","created":"2023-09-29","cited_by_count":6},{"id":"2210.04158","title":"HVS Revisited: A Comprehensive Video Quality Assessment Framework","created":"2022-10-09","cited_by_count":5},{"id":"2303.06254","title":"Rate-Distortion Optimization With Alternative References For UGC Video Compression","created":"2023-03-11","cited_by_count":3},{"id":"2203.03553","title":"Compression of user generated content using denoised references","created":"2022-03-07","cited_by_count":1}],"next_cursor":null}