The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their temporal relation
ship which are crucial for general video understanding. To address these challenges, this paper proposes a multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations. Concretely, high-level features obtained from naive and prototypical contrastive learning are utilized to build distribution graphs, guiding the process of low-level and mid-level feature learning. We also devise a simple temporal modeling module from multi-level features to enhance motion pattern learning. Experiments demonstrate that multi-level feature optimization with the graph constraint and temporal modeling can greatly improve the representation ability in video understanding. Code is available at https://github.com/shvdiwnkozbw/Video-Representation-via-Multi-level-Optimization.
Few-shot action recognition aims to recognize novel action classes (query) using just a few samples (support). The majority of current approaches follow the metric learning paradigm, which learns to compare the similarity between videos. Recently, it
has been observed that directly measuring this similarity is not ideal since different action instances may show distinctive temporal distribution, resulting in severe misalignment issues across query and support videos. In this paper, we arrest this problem from two distinct aspects -- action duration misalignment and motion evolution misalignment. We address them sequentially through a Two-stage Temporal Alignment Network (TTAN). The first stage performs temporal transformation with the predicted affine warp parameters, while the second stage utilizes a cross-attention mechanism to coordinate the features of the support and query to a consistent evolution. Besides, we devise a novel multi-shot fusion strategy, which takes the misalignment among support samples into consideration. Ablation studies and visualizations demonstrate the role played by both stages in addressing the misalignment. Extensive experiments on benchmark datasets show the potential of the proposed method in achieving state-of-the-art performance for few-shot action recognition.
Along with the development of modern smart cities, human-centric video analysis has been encountering the challenge of analyzing diverse and complex events in real scenes. A complex event relates to dense crowds, anomalous, or collective behaviors. H
owever, limited by the scale of existing video datasets, few human analysis approaches have reported their performance on such complex events. To this end, we present a new large-scale dataset, named Human-in-Events or HiEve (Human-centric video analysis in complex Events), for the understanding of human motions, poses, and actions in a variety of realistic events, especially in crowd and complex events. It contains a record number of poses (>1M), the largest number of action instances (>56k) under complex events, as well as one of the largest numbers of trajectories lasting for longer time (with an average trajectory length of >480 frames). Based on this dataset, we present an enhanced pose estimation baseline by utilizing the potential of action information to guide the learning of more powerful 2D pose features. We demonstrate that the proposed method is able to boost the performance of existing pose estimation pipelines on our HiEve dataset. Furthermore, we conduct extensive experiments to benchmark recent video analysis approaches together with our baseline methods, demonstrating that HiEve is a challenging dataset for human-centric video analysis. We expect that the dataset will advance the development of cutting-edge techniques in human-centric analysis and the understanding of complex events. The dataset is available at http://humaninevents.org
