Meta-Video: Efficient Standardized Evaluation for Video Understanding
University of Tübingen（蒂宾根大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；IBM Research（IBM研究院）；MIT（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Tübingen AI Center（蒂宾根人工智能中心）
Soumya Shamarao Jahagirdar, Anna Kukleva, Vishaal Udandarao, Samuel Thomas, Brian Kingsbury, Rogerio Feris, James R. Glass, Ameya Prabhu, Hilde Kuehne
Video understanding benchmarks are the primary yardstick for measuring progress in video-language modeling, and a growing body of work relies on them to claim improvements. The reported benchmark scores in these works, however, are almost always produced by frameworks (e.g., lmms eval) used as black boxes: certain evaluation choices like frame sampling, preprocessing, and input formatting are inherited from preset defaults and seldom inspected carefully. We show these unexamined choices are a major source of variance. Even for the same model checkpoint, evaluation configuration alone can shift accuracy by up to 19.5pp. Hence, it is unclear whether reported gains reflect genuine improvements in capability or differences in evaluation setup. Moreover, many benchmark samples offer little evidence of visual capability, since they can be answered without the video, and the full suites are expensive to evaluate. We address these issues in two parts. First, we curate existing suites for discriminability and efficiency, producing Meta-Video, a balanced 1,000-question benchmark over 791 videos spanning diverse tasks and durations, which largely preserves model rankings, at 5 times inference speedup for a full-frame count sweep experiment (4-128 frames). Second, we establish a standardized evaluation protocol by sweeping the configuration space to isolate choices that measurably affect results, distill them into best practices and reporting standards, and release reproducible reference scores across five models and seven benchmarks. We hope that the proposed evaluation framework and the Meta-Video benchmark will support video understanding research by providing a reproducible and efficient foundation to measure progress in a reliable way. Project page: https://soumyasj.github.io/meta-video/
MetaphorVU: Towards Metaphorical Video Understanding
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所信息处理实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Department of Automation, Tsinghua University（清华大学自动化系）
Multiple Object Tracking in Video SAR: A Benchmark and Tracking Baseline
School of Electronic and Information Engineering, Beihang University（北京航空航天大学电子信息工程学院）；Beijing Institute of Control and Electronics Technology（北京控制与电子技术研究所）
ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding
Chongqing University（重庆大学）；Tianjin University（天津大学）；MAIS, Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院MAIS）；Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore（新加坡科技研究局高性能计算研究所）；Chongqing National Data AI Research Institute, AI Research Lab（重庆国家数据AI研究院，AI研究实验室）
Spatiotemporal Action Recognition in Restaurant Videos
Carnegie Mellon University（卡内基梅隆大学）
时空动作识别是对视频中的动作进行定位和分类的任务。我们的项目将此任务应用于分析餐厅工作人员准备食物的视频片段，其潜在应用包括自动结账和库存管理。这些视频与研究人员习惯的标准化数据集截然不同，因为它们涉及小对象，快速动作和众所周知的不平衡数据类。我们探索两种方法。第一种方法涉及熟悉的对象检测器You Only Look Once，另一种方法应用最近提出的动作识别模拟，You Only Watch Once。首先，我们使用卷积LSTM设计并实现了一种新颖的、经常性的YOLO修改，并探索了这种网络训练中的各种微妙之处。在第二部分中，我们研究了YOWO三维卷积捕捉我们独特数据集的时空特征的能力
How Well Can General Vision-Language Models Learn Medicine By Watching Public Educational Videos?
Stanford University（斯坦福大学）；Together AI；University of California, Berkeley（加州大学伯克利分校）；Cedars-Sinai Medical Center（西德斯-西奈医学中心）；University of California, San Francisco（加州大学旧金山分校）
MetaDance: Few-shot Dancing Video Retargeting via Temporal-aware Meta-learning
The University of Hong Kong（香港大学）；Tencent AI Lab（腾讯人工智能实验室）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
University of Southern California（南加州大学）；Iterable, Inc.（Iterable公司）；University of Virginia（弗吉尼亚大学）；University of Waterloo（滑铁卢大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）；RISE - Research Institutes of Sweden, SICS（瑞典研究院SICS）
vCLIMB: A Novel Video Class Incremental Learning Benchmark
Pontificia Universidad Católica de Chile（智利天主教大学）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））；Samsung AI Center Cambridge（三星剑桥人工智能中心）；Adobe Research（奥多比研究院）
One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video
The Chinese University of Hong Kong（香港中文大学）；T stone Robotics Institute（T石头机器人研究所）；Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems（粤港澳人机协同智能系统联合实验室）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
