Related papers: Leveraging Motion Information for Better Self-Supe…

Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…

Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of…

Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…

Music emotion recognition (MER) aims to identify the emotions conveyed in a given musical piece. However, currently, in the field of MER, the available public datasets have limited sample sizes. Recently, segment-based methods for…

Though quite challenging, leveraging large-scale unlabeled or partially labeled images in a cost-effective way has increasingly attracted interests for its great importance to computer vision. To tackle this problem, many Active Learning…

Temporal correspondence - linking pixels or objects across frames - is a fundamental supervisory signal for the video models. For the panoptic understanding of dynamic scenes, we further extend this concept to every segment. Specifically,…

Unsupervised video object segmentation aims to segment a target object in the video without a ground truth mask in the initial frame. This challenging task requires extracting features for the most salient common objects within a video…

Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image formation model and use hand-crafted priors: they usually produce…

Most state-of-the-art semi-supervised video object segmentation methods rely on a pixel-accurate mask of a target object provided for the first frame of a video. However, obtaining a detailed segmentation mask is expensive and…

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…

Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric…

We propose a self-supervised visual learning method by predicting the variable playback speeds of a video. Without semantic labels, we learn the spatio-temporal visual representation of the video by leveraging the variations in the visual…

We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted…

Existing deep learning based unsupervised video object segmentation methods still rely on ground-truth segmentation masks to train. Unsupervised in this context only means that no annotated frames are used during inference. As obtaining…

Hyperspectral target detection is a pixel-level recognition problem. Given a few target samples, it aims to identify the specific target pixels such as airplane, vehicle, ship, from the entire hyperspectral image. In general, the background…

This paper investigates the principles of embedding learning to tackle the challenging semi-supervised video object segmentation. Different from previous practices that only explore the embedding learning using pixels from foreground object…

Existing pedestrian attribute recognition (PAR) algorithms are mainly developed based on a static image. However, the performance is not reliable for images with challenging factors, such as heavy occlusion, motion blur, etc. In this work,…

At the most basic level, pixels are the source of the visual information through which we perceive the world. Pixels contain information at all levels, ranging from low-level attributes to high-level concepts. Autoencoders represent a…

We present an unsupervised representation learning approach using videos without semantic labels. We leverage the temporal coherence as a supervisory signal by formulating representation learning as a sequence sorting task. We take…