{"total":24,"rows":[{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991,"area":null},{"id":"2207.08954","title":"Exploiting Unlabeled Data with Vision and Language Models for Object Detection","created":"2022-07-18","cited_by_count":97,"area":null},{"id":"2304.01195","title":"Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement","created":"2023-04-03","cited_by_count":84,"area":null},{"id":"2304.04909","title":"SATR: Zero-Shot Semantic Segmentation of 3D Shapes","created":"2023-04-11","cited_by_count":62,"area":null},{"id":"2303.02982","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2304.08386","title":"Progressive Visual Prompt Learning with Contrastive Feature Re-formation","created":"2023-04-17","cited_by_count":36,"area":null},{"id":"2210.03919","title":"CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation","created":"2022-10-08","cited_by_count":19,"area":null},{"id":"2308.07539","title":"Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2205.07056","title":"Transformer Scale Gate for Semantic Segmentation","created":"2022-05-14","cited_by_count":17,"area":null},{"id":"2310.03324","title":"Investigating the Limitation of CLIP Models: The Worst-Performing Categories","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2211.07275","title":"Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment","created":"2022-11-14","cited_by_count":8,"area":null},{"id":"2307.03339","title":"Open-Vocabulary Object Detection via Scene Graph Discovery","created":"2023-07-07","cited_by_count":7,"area":null},{"id":"2408.10641","title":"A Review of Human-Object Interaction Detection","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2303.03144","title":"IPA-CLIP: Integrating Phonetic Priors into Vision and Language Pretraining","created":"2023-03-06","cited_by_count":4,"area":null},{"id":"2403.18969","title":"A Survey on Large Language Models from Concept to Implementation","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2407.11503","title":"Beyond Mask: Rethinking Guidance Types in Few-shot Segmentation","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2408.04102","title":"ArtVLM: Attribute Recognition Through Vision-Based Prefix Language Modeling","created":"2024-08-07","cited_by_count":2,"area":null},{"id":"2309.00696","title":"AAN: Attributes-Aware Network for Temporal Action Detection","created":"2023-09-01","cited_by_count":1,"area":null},{"id":"2401.00260","title":"GazeCLIP: Enhancing Gaze Estimation Through Text-Guided Multimodal Learning","created":"2023-12-30","cited_by_count":1,"area":null},{"id":"2303.09608","title":"VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object Detection","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2304.13130","title":"Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2306.06149","title":"Read, look and detect: Bounding box annotation from image-caption pairs","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2508.09446","title":"MPT: Motion Prompt Tuning for Micro-Expression Recognition","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2512.01213","title":"Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations","created":"2025-12-01","cited_by_count":0,"area":null}],"next_cursor":null}