Related papers: Time-Equivariant Contrastive Video Representation …

In this paper, we propose to learn temporal embeddings of video frames for complex video analysis. Large quantities of unlabeled video data can be easily obtained from the Internet. These videos possess the implicit weak label that they are…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods encounter limitations…

Despite the success of a number of recent techniques for visual self-supervised deep learning, there has been limited investigation into the representations that are ultimately learned. By leveraging recent advances in the comparison of…

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on…

Multi-channel video-language retrieval require models to understand information from different channels (e.g. video$+$question, video$+$speech) to correctly link a video with a textual response or query. Fortunately, contrastive multimodal…

The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to…

Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long…

This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce…

Online tracking of multiple objects in videos requires strong capacity of modeling and matching object appearances. Previous methods for learning appearance embedding mostly rely on instance-level matching without considering the temporal…

A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias. While most existing works implicitly achieve this with video-specific pretext tasks (e.g., predicting…

Learning decent representations from unlabeled time-series data with temporal dynamics is a very challenging task. In this paper, we propose an unsupervised Time-Series representation learning framework via Temporal and Contextual…

Video moment retrieval aims to search the moment most relevant to a given language query. However, most existing methods in this community often require temporal boundary annotations which are expensive and time-consuming to label. Hence…

The objective of this paper is self-supervised representation learning, with the goal of solving semi-supervised video object segmentation (a.k.a. dense tracking). We make the following contributions: (i) we propose to improve the existing…

The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections. To alleviate this problem, in this paper, we propose…

The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for…

Street view imagery is extensively utilized in representation learning for urban visual environments, supporting various sustainable development tasks such as environmental perception and socio-economic assessment. However, it is…

In an effort to reduce annotation costs in action recognition, unsupervised video domain adaptation methods have been proposed that aim to adapt a predictive model from a labelled dataset (i.e., source domain) to an unlabelled dataset…

Recently, contrastive self-supervised learning has become a key component for learning visual representations across many computer vision tasks and benchmarks. However, contrastive learning in the context of domain adaptation remains…

We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition. This task, however, is extremely…