Related papers: Removing the Background by Adding the Background: …

Deep learning has led to remarkable advances in computer vision. Even so, today's best models are brittle when presented with variations that differ even slightly from those seen during training. Minor shifts in the pose, color, or…

Self-supervised learning of depth map prediction and motion estimation from monocular video sequences is of vital importance -- since it realizes a broad range of tasks in robotics and autonomous vehicles. A large number of research efforts…

This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to…

Scene depth estimation from stereo and monocular imagery is critical for extracting 3D information for downstream tasks such as scene understanding. Recently, learning-based methods for depth estimation have received much attention due to…

Unsupervised object-centric learning aims to represent the modular, compositional, and causal structure of a scene as a set of object representations and thereby promises to resolve many critical limitations of traditional single-vector…

Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on…

When video is shot in noisy environment, the voice of a speaker seen in the video can be enhanced using the visible mouth movements, reducing background noise. While most existing methods use audio-only inputs, improved performance is…

Query-based video grounding is an important yet challenging task in video understanding, which aims to localize the target segment in an untrimmed video according to a sentence query. Most previous works achieve significant progress by…

Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterparts in some downstream tasks. Such approaches employ data…

Bias in machine learning models can lead to unfair decision making, and while it has been well-studied in the image and text domains, it remains underexplored in action recognition. Action recognition models often suffer from background…

Deep neural networks have become a foundational tool for addressing imaging inverse problems. They are typically trained for a specific task, with a supervised loss to learn a mapping from the observations to the image to recover. However,…

The remarkable success of deep learning in various domains relies on the availability of large-scale annotated datasets. However, obtaining annotations is expensive and requires great effort, which is especially challenging for videos.…

Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires…

Although the advances of self-supervised blind denoising are significantly superior to conventional approaches without clean supervision in synthetic noise scenarios, it shows poor quality in real-world images due to spatially correlated…

Identifying and mitigating bias in deep learning algorithms has gained significant popularity in the past few years due to its impact on the society. Researchers argue that models trained on balanced datasets with good representation…

Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…

Video Question Answering (Video QA) requires fine-grained understanding of both video and language modalities to answer the given questions. In this paper, we propose novel training schemes for multiple-choice video question answering with…

Foreground-background separation is an important problem in document image analysis. Popular unsupervised binarization methods (such as the Sauvola's algorithm) employ adaptive thresholding to classify pixels as foreground or background. In…

In natural image matting, the goal is to estimate the opacity of the foreground object in the image. This opacity controls the way the foreground and background is blended in transparent regions. In recent years, advances in deep learning…

Collaborative perception enhances the reliability and spatial coverage of autonomous vehicles by sharing complementary information across vehicles, offering a promising solution to long-tail scenarios that challenge single-vehicle…