相关论文: Long Short View Feature Decomposition via Contrast…
Video representation learning has recently attracted attention in computer vision due to its applications for activity and scene forecasting or vision-based planning and control. Video prediction models often learn a latent representation…
We use multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length representation. This representation is decoded using single or…
Contrastive learning has shown promising potential in self-supervised spatio-temporal representation learning. Most works naively sample different clips to construct positive and negative pairs. However, we observe that this formulation…
Stochastic video prediction enables the consideration of uncertainty in future motion, thereby providing a better reflection of the dynamic nature of the environment. Stochastic video prediction methods based on image auto-regressive…
We propose a method for representing motion information for video classification and retrieval. We improve upon local descriptor based methods that have been among the most popular and successful models for representing videos. The desired…
Video summarization aims to select the most informative subset of frames in a video to facilitate efficient video browsing. Unsupervised methods usually rely on heuristic training objectives such as diversity and representativeness.…
Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long…
Most of human actions consist of complex temporal compositions of more simple actions. Action recognition tasks usually relies on complex handcrafted structures as features to represent the human action model. Convolutional Neural Nets…
Referring video segmentation relies on natural language expressions to identify and segment objects, often emphasizing motion clues. Previous works treat a sentence as a whole and directly perform identification at the video-level, mixing…
Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time. This leads to loss of pertinent information related to…
While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot provide reliable predictions for scenes with a moving camera…
In this study, we investigate the impact of online pre-training with continuous video clips. We will examine three methods for pre-training (masked image modeling, contrastive learning, and knowledge distillation), and assess the…
Generated video scenes for action-centric sequence descriptions, such as recipe instructions and do-it-yourself projects, often include non-linear patterns, where the next video may need to be visually consistent not with the immediately…
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture…
In this paper, we introduce an end-to-end framework for video analysis focused towards practical scenarios built on theoretical foundations from sparse representation, including a novel descriptor for general purpose video analysis. In our…
Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the…
Temporal reasoning is an important aspect of video analysis. 3D CNN shows good performance by exploring spatial-temporal features jointly in an unconstrained way, but it also increases the computational cost a lot. Previous works try to…
In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervised fashion from unlabeled images or videos, using carefully…
While deep feature learning has revolutionized techniques for static-image understanding, the same does not quite hold for video processing. Architectures and optimization techniques used for video are largely based off those for static…
How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact…