{"list":"other","total":75,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"id":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219},{"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":"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":"2206.07045","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","created":"2022-06-14","cited_by_count":117},{"id":"2212.04994","title":"Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning","created":"2022-12-09","cited_by_count":115},{"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":"2310.15308","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding","created":"2023-10-23","cited_by_count":111},{"id":"2408.04883","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","created":"2024-08-09","cited_by_count":111},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108},{"id":"2301.09121","title":"Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision","created":"2023-01-22","cited_by_count":99},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93},{"id":"2301.02280","title":"Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training","created":"2023-01-05","cited_by_count":91},{"id":"2312.00878","title":"Grounding Everything: Emerging Localization Properties in Vision-Language Transformers","created":"2023-12-01","cited_by_count":91},{"id":"2303.06594","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","created":"2023-03-12","cited_by_count":86},{"id":"2404.08181","title":"Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation","created":"2024-04-12","cited_by_count":77},{"id":"2309.02773","title":"Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter","created":"2023-09-06","cited_by_count":76},{"id":"2310.07699","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","created":"2023-10-11","cited_by_count":70},{"id":"2312.07661","title":"CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor","created":"2023-12-12","cited_by_count":69},{"id":"2306.09316","title":"Diffusion Models for Open-Vocabulary Segmentation","created":"2023-06-15","cited_by_count":64},{"id":"2407.08268","title":"Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation","created":"2024-07-11","cited_by_count":61},{"id":"2404.06542","title":"Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation","created":"2024-04-09","cited_by_count":44},{"id":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","cited_by_count":41},{"id":"2309.14289","title":"CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free","created":"2023-09-25","cited_by_count":39},{"id":"2310.02110","title":"Sieve: Multimodal Dataset Pruning Using Image Captioning Models","created":"2023-10-03","cited_by_count":33},{"id":"2309.13505","title":"Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation","created":"2023-09-24","cited_by_count":21},{"id":"2404.04231","title":"Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation","created":"2024-04-05","cited_by_count":21},{"id":"2404.09447","title":"kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies","created":"2024-04-15","cited_by_count":20},{"id":"2303.11126","title":"Robustifying Token Attention for Vision Transformers","created":"2023-03-20","cited_by_count":19},{"id":"2305.05095","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","created":"2023-05-08","cited_by_count":19},{"id":"2303.13396","title":"Zero-guidance Segmentation Using Zero Segment Labels","created":"2023-03-23","cited_by_count":18},{"id":"2311.17095","title":"Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models","created":"2023-11-28","cited_by_count":15},{"id":"2404.00262","title":"Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation","created":"2024-03-30","cited_by_count":15},{"id":"2304.07547","title":"TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation","created":"2023-04-15","cited_by_count":14},{"id":"2406.05271","title":"USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation","created":"2024-06-07","cited_by_count":14},{"id":"2110.13252","title":"VAC-CNN: A Visual Analytics System for Comparative Studies of Deep Convolutional Neural Networks","created":"2021-10-25","cited_by_count":11},{"id":"2003.14407","title":"Probabilistic Pixel-Adaptive Refinement Networks","created":"2020-03-31","cited_by_count":8},{"id":"2303.17820","title":"LabelVizier: Interactive Validation and Relabeling for Technical Text Annotations","created":"2023-03-31","cited_by_count":7},{"id":"2401.06462","title":"AttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding","created":"2024-01-12","cited_by_count":6},{"id":"2303.00244","title":"SUNY: A Visual Interpretation Framework for Convolutional Neural Networks from a Necessary and Sufficient Perspective","created":"2023-03-01","cited_by_count":5},{"id":"2407.05594","title":"SLIM: Spuriousness Mitigation with Minimal Human Annotations","created":"2024-07-08","cited_by_count":5},{"id":"2505.03132","title":"VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis","created":"2025-05-06","cited_by_count":5},{"id":"2405.03234","title":"A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series","created":"2024-05-06","cited_by_count":3}],"next_cursor":null}