Related papers: Motion-Focused Contrastive Learning of Video Repre…

Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of…

Motion retrieval is crucial for motion acquisition, offering superior precision, realism, controllability, and editability compared to motion generation. Existing approaches leverage contrastive learning to construct a unified embedding…

Learning with neural networks from a continuous stream of visual information presents several challenges due to the non-i.i.d. nature of the data. However, it also offers novel opportunities to develop representations that are consistent…

Contrastive learning (CL) has become a powerful approach for learning representations from unlabeled images. However, existing CL methods focus predominantly on visual appearance features while neglecting topological characteristics (e.g.,…

Generalized Category Discovery (GCD) is an emerging and challenging open-world problem that has garnered increasing attention in recent years. Most existing GCD methods focus on discovering categories in static images. However, relying…

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without…

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…

Analyzing periodic video sequences is a key topic in applications such as automatic production systems, remote sensing, medical applications, or physical training. An example is counting repetitions of a physical exercise. Due to the…

Video contrastive learning (V-CL) has emerged as a popular framework for unsupervised video representation learning, demonstrating strong results in tasks such as action classification and detection. Yet, to harness these benefits, it is…

Multimodal representation learning is a challenging task in which previous work mostly focus on either uni-modality pre-training or cross-modality fusion. In fact, we regard modeling multimodal representation as building a skyscraper, where…

Given a collection of untrimmed and unsegmented videos, video corpus moment retrieval (VCMR) is to retrieve a temporal moment (i.e., a fraction of a video) that semantically corresponds to a given text query. As video and text are from two…

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as…

Accurate fetal movement (FM) detection is essential for assessing prenatal health, as abnormal movement patterns can indicate underlying complications such as placental dysfunction or fetal distress. Traditional methods, including maternal…

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…

Instance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning. They are not suitable for exploiting the rich…

Visual tempo, which describes how fast an action goes, has shown its potential in supervised action recognition. In this work, we demonstrate that visual tempo can also serve as a self-supervision signal for video representation learning.…

Current state-of-the-art approaches for few-shot action recognition achieve promising performance by conducting frame-level matching on learned visual features. However, they generally suffer from two limitations: i) the matching procedure…

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…

Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence. We suspect this behavior is due to the suboptimal selection of negatives used for…

Contrastive learning has revolutionized self-supervised image representation learning field, and recently been adapted to video domain. One of the greatest advantages of contrastive learning is that it allows us to flexibly define powerful…