Video segmentation is a stepping stone to understanding video context. Video segmentation enables one to represent a video by decomposing it into coherent regions which comprise whole or parts of objects. However, the challenge originates from the fact that most of the video segmentation algorithms are based on unsupervised learning due to expensive cost of pixelwise video annotation and intra-class variability within similar unconstrained video classes. We propose a Markov Random Field model for unconstrained video segmentation that relies on tight integration of multiple cues: vertices are defined from contour based superpixels, unary potentials from temporal smooth label likelihood and pairwise potentials from global structure of a video. Multi-cue structure is a breakthrough to extracting coherent object regions for unconstrained videos in absence of supervision. Our experiments on VSB100 dataset show that the proposed model significantly outperforms competing state-of-the-art algorithms. Qualitative analysis illustrates that video segmentation result of the proposed model is consistent with human perception of objects.
Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues
UC Berkeley（加州大学伯克利分校）；Facebook AI Research（Facebook人工智能研究院）
我们探讨了在一个不受约束的设置中识别相册中的人的身份的任务。为了促进这一点，我们介绍了新的人在相册（PIPA）数据集，包括超过60000个实例的2000个人从公共Flickr相册收集。由于只有大约一半的人的图像包含正面的脸，识别任务是非常具有挑战性的，由于姿势，服装，相机的观点，图像分辨率和照明的大变化。我们提出了Pose Invariant PErson Recognition（PIPER）方法，该方法积累了由深度卷积网络训练的poselet级别的人识别器的线索，以折扣姿态变化，结合面部识别器和全局识别器。在三种不同设置上的实验证实，在我们的无约束设置中，PIPER显着提高了DeepFace的性能，DeepFace是在LFW数据集上测量的最佳人脸识别器之一。
Finger in Camera Speaks Everything: Unconstrained Air-Writing for Real-World
University of Chinese Academy of Sciences（中国科学院大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding
Inria, Université Côte d’Azur, France（法国国家信息与自动化研究所、法国滨海阿尔卑斯大学）；Hanyang University, South Korea（韩国家阳大学）；Pusan National University, South Korea（韩国釜山国立大学）
Periocular Biometrics: A Modality for Unconstrained Scenarios
School of Information Technology, Halmstad University（哈尔姆斯塔德大学信息技术学院）；School of Engineering, Universidad Autonoma de Madrid（马德里自治大学工程学院）；Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究所）；TU Darmstadt（达姆施塔特工业大学）；Department of Computer Science and Engineering, Michigan State University（密歇根州立大学计算机科学与工程系）
MVRD-Bench: Multi-View Learning and Benchmarking for Dynamic Remote Photoplethysmography under Occlusion
Nanjing University of Information Science and Technology（南京信息工程大学）；University of Oulu（奥卢大学）；Xi’an Jiaotong University（西安交通大学）；Zhejiang University（浙江大学）
Universidade Federal de Pernambuco（伯南布哥联邦大学）；University of Montreal（蒙特利尔大学）；Northwestern University（西北大学）；Universidade Federal Rural de Pernambuco（伯南布哥联邦农村大学）
Investigating naturalistic hand movements by behavior mining in long-term video and neural recordings
University of Washington（华盛顿大学）；Center for Neurotechnology（神经技术中心）；University of Washington Institute for Neuroengineering（华盛顿大学神经工程研究所）；eScience Institute, University of Washington（华盛顿大学电子科学研究所）
FeatDistill: A Feature Distillation Enhanced Multi-Expert Ensemble Framework for Robust AI-generated Image Detection
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；State Key Laboratory of Internet of Things for Smart City, University of Macau（澳门大学物联网智能城市国家重点实验室）；PRADA Lab, King Abdullah University of Science and Technology（科学与技术王国大学PRADA实验室）；Department of Information Engineering, University of Florence（佛罗伦萨大学信息工程系）
Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
Carnegie Mellon University（卡内基梅隆大学）；University of Southern California（南加州大学）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究院）；The Hong Kong Polytechnic University（香港理工大学）
OSA: Echocardiography Video Segmentation via Orthogonalized State Update and Anatomical Prior-aware Feature Enhancement
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；Centre for Smart Health, School of Nursing, The Hong Kong Polytechnic University（香港理工大学护理学院智能健康中心）
