{"total":23,"rows":[{"id":"2404.16687","title":"NTIRE 2024 Quality Assessment of AI-Generated Content Challenge","created":"2024-04-25","cited_by_count":20,"area":null},{"id":"2108.08363","title":"Social Fabric: Tubelet Compositions for Video Relation Detection","created":"2021-08-18","cited_by_count":18,"area":null},{"id":"2110.14381","title":"Temporal-attentive Covariance Pooling Networks for Video Recognition","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2203.15381","title":"Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification","created":"2022-03-29","cited_by_count":11,"area":null},{"id":"2209.12164","title":"Multi-modal Segment Assemblage Network for Ad Video Editing with Importance-Coherence Reward","created":"2022-09-25","cited_by_count":10,"area":null},{"id":"2210.00132","title":"Alignment-guided Temporal Attention for Video Action Recognition","created":"2022-09-30","cited_by_count":10,"area":null},{"id":"2308.14052","title":"MM-AU:Towards Multimodal Understanding of Advertisement Videos","created":"2023-08-27","cited_by_count":8,"area":null},{"id":"2109.07951","title":"Overview of Tencent Multi-modal Ads Video Understanding Challenge","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2202.02516","title":"A Survey on Automated Sarcasm Detection on Twitter","created":"2022-02-05","cited_by_count":3,"area":null},{"id":"2303.08318","title":"Micro-video Tagging via Jointly Modeling Social Influence and Tag Relation","created":"2023-03-15","cited_by_count":3,"area":null},{"id":"2407.19894","title":"CardioSyntax: end-to-end SYNTAX score prediction -- dataset, benchmark and method","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2409.19293","title":"VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition","created":"2024-09-28","cited_by_count":3,"area":null},{"id":"2209.06170","title":"Computational Sarcasm Analysis on Social Media: A Systematic Review","created":"2022-09-13","cited_by_count":2,"area":null},{"id":"2212.04700","title":"Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation","created":"2022-12-09","cited_by_count":2,"area":null},{"id":"2306.10079","title":"M3PT: A Multi-Modal Model for POI Tagging","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2108.12868","title":"A Multimodal Framework for Video Ads Understanding","created":"2021-08-29","cited_by_count":1,"area":null},{"id":"2306.03835","title":"Atrial Septal Defect Detection in Children Based on Ultrasound Video Using Multiple Instances Learning","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2311.00800","title":"Beyond still images: Temporal features and input variance resilience","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2501.12524","title":"Efficient Lung Ultrasound Severity Scoring Using Dedicated Feature Extractor","created":"2025-01-21","cited_by_count":1,"area":null},{"id":"2503.00054","title":"Deciphering the complaint aspects: Towards an aspect-based complaint identification model with video complaint dataset in finance","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2608.16797","title":"UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendation","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2502.07277","title":"Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis","created":"2025-02-11","cited_by_count":0,"area":null},{"id":"2609.04369","title":"AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}