{"list":"other","total":72,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1712.04621","title":"The Effectiveness of Data Augmentation in Image Classification using Deep Learning","created":"2017-12-13","cited_by_count":370},{"id":"1803.10464","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","created":"2018-03-28","cited_by_count":321},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2004.04581","title":"Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation","created":"2020-04-09","cited_by_count":300},{"id":"1903.07593","title":"Learning Correspondence from the Cycle-Consistency of Time","created":"2019-03-18","cited_by_count":269},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"1904.05044","title":"Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations","created":"2019-04-10","cited_by_count":247},{"id":"2006.14613","title":"Space-Time Correspondence as a Contrastive Random Walk","created":"2020-06-25","cited_by_count":239},{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236},{"id":"2201.00424","title":"Splicing ViT Features for Semantic Appearance Transfer","created":"2022-01-02","cited_by_count":209},{"id":"2312.01597","title":"SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference","created":"2023-12-04","cited_by_count":170},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163},{"id":"2305.13310","title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","created":"2023-05-22","cited_by_count":142},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"2203.02891","title":"Multi-class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2022-03-06","cited_by_count":138},{"id":"2212.00785","title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","created":"2022-12-01","cited_by_count":130},{"id":"2212.09506","title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","created":"2022-12-16","cited_by_count":118},{"id":"2206.07045","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","created":"2022-06-14","cited_by_count":117},{"id":"2005.02551","title":"CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement","created":"2020-05-06","cited_by_count":113},{"id":"2309.14303","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","created":"2023-09-25","cited_by_count":112},{"id":"2004.13324","title":"Learning Feature Descriptors using Camera Pose Supervision","created":"2020-04-28","cited_by_count":104},{"id":"2301.09121","title":"Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision","created":"2023-01-22","cited_by_count":99},{"id":"2111.12698","title":"Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling","created":"2021-11-24","cited_by_count":84},{"id":"2108.03852","title":"Complementary Patch for Weakly Supervised Semantic Segmentation","created":"2021-08-09","cited_by_count":75},{"id":"2207.08455","title":"Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding","created":"2022-07-18","cited_by_count":67},{"id":"2303.01267","title":"Token Contrast for Weakly-Supervised Semantic Segmentation","created":"2023-03-02","cited_by_count":65},{"id":"2105.06464","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","created":"2021-05-13","cited_by_count":59},{"id":"1704.01740","title":"Object-Part Attention Model for Fine-grained Image Classification","created":"2017-04-06","cited_by_count":54},{"id":"2303.09813","title":"DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery","created":"2023-03-17","cited_by_count":54},{"id":"2403.05131","title":"Sora as a World Model? A Complete Survey on Text-to-Video Generation","created":"2024-03-08","cited_by_count":53},{"id":"2302.10307","title":"ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency","created":"2023-01-31","cited_by_count":51},{"id":"2404.06542","title":"Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation","created":"2024-04-09","cited_by_count":44},{"id":"2105.00957","title":"Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning","created":"2021-05-03","cited_by_count":43},{"id":"1702.00926","title":"FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence","created":"2017-02-03","cited_by_count":42},{"id":"2210.17400","title":"Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation","created":"2022-10-31","cited_by_count":41},{"id":"2003.06883","title":"Night-time Scene Parsing with a Large Real Dataset","created":"2020-03-15","cited_by_count":37},{"id":"2108.00211","title":"Multi-scale Matching Networks for Semantic Correspondence","created":"2021-07-31","cited_by_count":32},{"id":"2004.00705","title":"Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition","created":"2020-04-01","cited_by_count":31},{"id":"2105.12405","title":"Unsupervised Part Segmentation through Disentangling Appearance and Shape","created":"2021-05-26","cited_by_count":29},{"id":"2309.00096","title":"AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation","created":"2023-08-31","cited_by_count":29},{"id":"2403.11074","title":"Audio-Visual Segmentation via Unlabeled Frame Exploitation","created":"2024-03-17","cited_by_count":28},{"id":"2310.19001","title":"Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation","created":"2023-10-29","cited_by_count":27},{"id":"2302.13765","title":"Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation","created":"2023-02-27","cited_by_count":26},{"id":"2304.01184","title":"WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation","created":"2023-04-03","cited_by_count":22},{"id":"2307.02003","title":"Multi-Modal Prototypes for Open-World Semantic Segmentation","created":"2023-07-05","cited_by_count":22},{"id":"2304.04442","title":"Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection","created":"2023-04-10","cited_by_count":20},{"id":"1911.12950","title":"Deep Object Co-segmentation via Spatial-Semantic Network Modulation","created":"2019-11-29","cited_by_count":15},{"id":"2109.10967","title":"Learning Contrastive Representation for Semantic Correspondence","created":"2021-09-22","cited_by_count":12},{"id":"2307.09362","title":"Disentangle then Parse:Night-time Semantic Segmentation with Illumination Disentanglement","created":"2023-07-18","cited_by_count":12},{"id":"2403.20249","title":"Relation Rectification in Diffusion Model","created":"2024-03-29","cited_by_count":6},{"id":"2303.02449","title":"Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation","created":"2023-03-04","cited_by_count":2},{"id":"2307.07413","title":"Exploiting Counter-Examples for Active Learning with Partial labels","created":"2023-07-14","cited_by_count":1}],"next_cursor":null}