{"total":15,"rows":[{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314,"area":null},{"id":"2305.11003","title":"Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping","created":"2023-05-18","cited_by_count":92,"area":null},{"id":"2308.03166","title":"Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects","created":"2023-08-06","cited_by_count":56,"area":null},{"id":"2403.08268","title":"Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts","created":"2024-03-13","cited_by_count":52,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2306.03802","title":"Learning to Ground Instructional Articles in Videos through Narrations","created":"2023-06-06","cited_by_count":28,"area":null},{"id":"2402.17433","title":"Enhancing EEG-to-Text Decoding through Transferable Representations from Pre-trained Contrastive EEG-Text Masked Autoencoder","created":"2024-02-27","cited_by_count":15,"area":null},{"id":"2412.06340","title":"UniPaint: Unified Space-time Video Inpainting via Mixture-of-Experts","created":"2024-12-09","cited_by_count":13,"area":null},{"id":"2305.06472","title":"ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2408.05966","title":"Freehand Sketch Generation from Mechanical Components","created":"2024-08-12","cited_by_count":8,"area":null},{"id":"2501.10787","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","created":"2025-01-18","cited_by_count":8,"area":null},{"id":"2302.05940","title":"SemanticAC: Semantics-Assisted Framework for Audio Classification","created":"2023-02-12","cited_by_count":7,"area":null},{"id":"2305.07910","title":"Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval","created":"2023-05-13","cited_by_count":5,"area":null},{"id":"2312.10899","title":"MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising","created":"2023-12-18","cited_by_count":2,"area":null},{"id":"2408.02245","title":"A Two-Stage Progressive Pre-training using Multi-Modal Contrastive Masked Autoencoders","created":"2024-08-05","cited_by_count":0,"area":null}],"next_cursor":null}