Related papers: Consistent View Alignment Improves Foundation Mode…

Labeling videos at scale is impractical. Consequently, self-supervised visual representation learning is key for efficient video analysis. Recent success in learning image representations suggests contrastive learning is a promising…

Augmentation-based self-supervised learning methods have shown remarkable success in self-supervised visual representation learning, excelling in learning invariant features but often neglecting equivariant ones. This limitation reduces the…

We are concerned with a challenging scenario in unpaired multiview video learning. In this case, the model aims to learn comprehensive multiview representations while the cross-view semantic information exhibits variations. We propose…

We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data…

To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…

Presentation bias is one of the key challenges when learning from implicit feedback in search engines, as it confounds the relevance signal with uninformative signals due to position in the ranking, saliency, and other presentation factors.…

Although multi-view multi-label learning has been extensively studied, research on the dual-missing scenario, where both views and labels are incomplete, remains largely unexplored. Existing methods mainly rely on contrastive learning or…

Accurate and stable feature matching is critical for computer vision tasks, particularly in applications such as Simultaneous Localization and Mapping (SLAM). While recent learning-based feature matching methods have demonstrated promising…

Multiple views of data, both naturally acquired (e.g., image and audio) and artificially produced (e.g., via adding different noise to data samples), have proven useful in enhancing representation learning. Natural views are often handled…

We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video…

In this paper, we propose Multi-View Dreaming, a novel reinforcement learning agent for integrated recognition and control from multi-view observations by extending Dreaming. Most current reinforcement learning method assumes a single-view…

Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are…

Biological brains learn continually from a stream of unlabeled data, while integrating specialized information from sparsely labeled examples without compromising their ability to generalize. Meanwhile, machine learning methods are…

We address the problem of novel view synthesis: given an input image, synthesizing new images of the same object or scene observed from arbitrary viewpoints. We approach this as a learning task but, critically, instead of learning to…

Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does -…

Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous…

Current state-of-the-art methods cast monocular 3D human pose estimation as a learning problem by training neural networks on large data sets of images and corresponding skeleton poses. In contrast, we propose an approach that can exploit…

Currently almost all state-of-the-art novel view synthesis and reconstruction models rely on calibrated cameras or additional geometric priors for training. These prerequisites significantly limit their applicability to massive uncalibrated…

As the quality of synthetic images improves, identifying the underlying concepts of model-generated images is becoming increasingly crucial for copyright protection and ensuring model transparency. Existing methods achieve this attribution…

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…