相关论文: MC-JEPA: A Joint-Embedding Predictive Architecture…

Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in the context of environmental perception for vehicles due to…

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…

In this study, we investigate the task of data pre-selection, which aims to select instances for labeling from an unlabeled dataset through a single pass, thereby optimizing performance for undefined downstream tasks with a limited…

Video content is multifaceted, consisting of objects, scenes, interactions or actions. The existing datasets mostly label only one of the facets for model training, resulting in the video representation that biases to only one facet…

Learning depth and optical flow via deep neural networks by watching videos has made significant progress recently. In this paper, we jointly solve the two tasks by exploiting the underlying geometric rules within stereo videos.…

This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It roots from the observation that visual systems of human beings can easily identify video incoherence based on…

The recent emergence of Self-Supervised Learning (SSL) as a fundamental paradigm for learning image representations has, and continues to, demonstrate high empirical success in a variety of tasks. However, most SSL approaches fail to learn…

In recent years, semi-supervised learning has been widely explored and shows excellent data efficiency for 2D data. There is an emerging need to improve data efficiency for 3D tasks due to the scarcity of labeled 3D data. This paper…

Learning to predict future images from a video sequence involves the construction of an internal representation that models the image evolution accurately, and therefore, to some degree, its content and dynamics. This is why pixel-space…

Self-supervised tasks have been utilized to build useful representations that can be used in downstream tasks when the annotation is unavailable. In this paper, we introduce a self-supervised video representation learning method based on…

Event cameras offer promising properties, such as high temporal resolution and high dynamic range. These benefits have been utilized into many machine vision tasks, especially optical flow estimation. Currently, most existing event-based…

Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training models to output features for downstream use, we train them to…

Underwater degraded images greatly challenge existing algorithms to detect objects of interest. Recently, researchers attempt to adopt attention mechanisms or composite connections for improving the feature representation of detectors.…

Event cameras have the potential to capture continuous motion information over time and space, making them well-suited for optical flow estimation. However, most existing learning-based methods for event-based optical flow adopt frame-based…

Autonomous vehicle navigation is a key challenge in artificial intelligence, requiring robust and accurate decision-making processes. This research introduces a new end-to-end method that exploits multimodal information from a single…

Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical…

Temporal coherence is a valuable source of information in the context of optical flow estimation. However, finding a suitable motion model to leverage this information is a non-trivial task. In this paper we propose an unsupervised online…

Visual Speech Recognition (VSR) tasks are generally recognized to have a lower theoretical performance ceiling than Automatic Speech Recognition (ASR), owing to the inherent limitations of conveying semantic information visually. To…

Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers…

Cardiac motion estimation and segmentation play important roles in quantitatively assessing cardiac function and diagnosing cardiovascular diseases. In this paper, we propose a novel deep learning method for joint estimation of motion and…