{"list":"other","total":58,"rows":[{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"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":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"2303.09295","title":"DIRE for Diffusion-Generated Image Detection","created":"2023-03-16","cited_by_count":390},{"id":"1805.10421","title":"Enhanced-alignment Measure for Binary Foreground Map Evaluation","created":"2018-05-26","cited_by_count":370},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"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":"2304.04709","title":"Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection","created":"2023-04-10","cited_by_count":100},{"id":"2004.01241","title":"Semantic Segmentation of Underwater Imagery: Dataset and Benchmark","created":"2020-04-02","cited_by_count":95},{"id":"2311.16845","title":"Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration","created":"2023-11-28","cited_by_count":88},{"id":"1906.04402","title":"Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval","created":"2019-06-11","cited_by_count":83},{"id":"2307.08317","title":"AltFreezing for More General Video Face Forgery Detection","created":"2023-07-17","cited_by_count":78},{"id":"2208.06857","title":"Underwater Ranker: Learn Which Is Better and How to Be Better","created":"2022-08-14","cited_by_count":67},{"id":"2408.15994","title":"Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration","created":"2024-08-28","cited_by_count":62},{"id":"2212.06570","title":"CamoFormer: Masked Separable Attention for Camouflaged Object Detection","created":"2022-12-10","cited_by_count":58},{"id":"2009.03075","title":"Uncertainty Inspired RGB-D Saliency Detection","created":"2020-09-07","cited_by_count":56},{"id":"2203.03635","title":"Stepwise Feature Fusion: Local Guides Global","created":"2022-03-07","cited_by_count":56},{"id":"2303.09813","title":"DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery","created":"2023-03-17","cited_by_count":54},{"id":"2002.01155","title":"Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception","created":"2020-02-04","cited_by_count":53},{"id":"2407.12276","title":"VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation","created":"2024-07-17","cited_by_count":50},{"id":"2306.08918","title":"PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators","created":"2023-06-15","cited_by_count":49},{"id":"2405.04964","title":"Frequency-Assisted Mamba for Remote Sensing Image Super-Resolution","created":"2024-05-08","cited_by_count":48},{"id":"2406.09627","title":"RobustSAM: Segment Anything Robustly on Degraded Images","created":"2024-06-13","cited_by_count":36},{"id":"2211.16761","title":"Improving Cross-Modal Retrieval with Set of Diverse Embeddings","created":"2022-11-30","cited_by_count":33},{"id":"2309.03445","title":"Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip Strategy","created":"2023-09-07","cited_by_count":33},{"id":"2406.06039","title":"Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset","created":"2024-06-10","cited_by_count":33},{"id":"2312.12471","title":"Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion","created":"2023-12-19","cited_by_count":28},{"id":"2403.01497","title":"Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image Enhancement","created":"2024-03-03","cited_by_count":25},{"id":"2207.05921","title":"Texture-guided Saliency Distilling for Unsupervised Salient Object Detection","created":"2022-07-13","cited_by_count":24},{"id":"2404.04996","title":"Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM","created":"2024-04-07","cited_by_count":23},{"id":"2311.11273","title":"Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection","created":"2023-11-19","cited_by_count":22},{"id":"2501.12981","title":"UniUIR: Considering Underwater Image Restoration as An All-in-One Learner","created":"2025-01-22","cited_by_count":22},{"id":"2404.04231","title":"Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation","created":"2024-04-05","cited_by_count":21},{"id":"2011.06252","title":"SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots","created":"2020-11-12","cited_by_count":20},{"id":"2105.03053","title":"Salient Objects in Clutter","created":"2021-05-07","cited_by_count":19},{"id":"2306.03437","title":"DFormer: Diffusion-guided Transformer for Universal Image Segmentation","created":"2023-06-06","cited_by_count":19},{"id":"2306.07532","title":"Referring Camouflaged Object Detection","created":"2023-06-13","cited_by_count":19},{"id":"2108.05076","title":"Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation","created":"2021-08-11","cited_by_count":18},{"id":"2404.14542","title":"UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement","created":"2024-04-22","cited_by_count":18},{"id":"2405.01002","title":"Spider: A Unified Framework for Context-dependent Concept Segmentation","created":"2024-05-02","cited_by_count":18},{"id":"2308.03826","title":"Recurrent Multi-scale Transformer for High-Resolution Salient Object Detection","created":"2023-08-07","cited_by_count":15},{"id":"2404.15700","title":"MAS-SAM: Segment Any Marine Animal with Aggregated Features","created":"2024-04-24","cited_by_count":15},{"id":"2311.11241","title":"Open-Vocabulary Camouflaged Object Segmentation","created":"2023-11-19","cited_by_count":14},{"id":"2407.13133","title":"FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection","created":"2024-07-18","cited_by_count":14},{"id":"2403.14837","title":"Osmosis: RGBD Diffusion Prior for Underwater Image Restoration","created":"2024-03-21","cited_by_count":13},{"id":"2407.21654","title":"MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment","created":"2024-07-31","cited_by_count":9},{"id":"2410.05577","title":"Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future","created":"2024-10-08","cited_by_count":8},{"id":"2303.10383","title":"Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation","created":"2023-03-18","cited_by_count":7},{"id":"2408.02924","title":"Evaluation of Segment Anything Model 2: The Role of SAM2 in the Underwater Environment","created":"2024-08-06","cited_by_count":7},{"id":"2306.14141","title":"A Gated Cross-domain Collaborative Network for Underwater Object Detection","created":"2023-06-25","cited_by_count":5},{"id":"2209.12138","title":"Towards Stable Co-saliency Detection and Object Co-segmentation","created":"2022-09-25","cited_by_count":4}],"next_cursor":null}