Related papers: DMM-Net: Differentiable Mask-Matching Network for …

The Class Activation Map (CAM) lookup of a neural network tells us to which regions the neural network focuses when it makes a decision. In the past, the CAM search method was dependent upon a specific internal module of the network. It has…

A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi-scale object detection. The MS-CNN consists of a proposal sub-network and a detection sub-network. In the proposal sub-network, detection is…

Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constraint. We regard…

Dynamic Mode Decomposition (DMD) is a numerical method that seeks to fit timeseries data to a linear dynamical system. In doing so, DMD decomposes dynamic data into spatially coherent modes that evolve in time according to exponential…

Video instance segmentation aims at predicting object segmentation masks for each frame, as well as associating the instances across multiple frames. Recent end-to-end video instance segmentation methods are capable of performing object…

Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects. It becomes tremendously challenging when multiple objects occur and interact in a given video clip.…

Online zero-shot 3D instance segmentation of a progressively reconstructed scene is both a critical and challenging task for embodied applications. With the success of visual foundation models (VFMs) in the image domain, leveraging 2D…

The task of semi-supervised video object segmentation (VOS) has been greatly advanced and state-of-the-art performance has been made by dense matching-based methods. The recent methods leverage space-time memory (STM) networks and learn to…

Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down…

In this paper, the main task we aim to tackle is the multi-instance semi-supervised video object segmentation across a sequence of frames where only the first-frame box-level ground-truth is provided. Detection-based algorithms are widely…

The attributes of object contours has great significance for instance segmentation task. However, most of the current popular deep neural networks do not pay much attention to the object edge information. Inspired by the human annotation…

High-resolution remote sensing imagery increasingly contains dense clusters of tiny objects, the detection of which is extremely challenging due to severe mutual occlusion and limited pixel footprints. Existing detection methods typically…

Disparity prediction from stereo images is essential to computer vision applications including autonomous driving, 3D model reconstruction, and object detection. To predict accurate disparity map, we propose a novel deep learning…

In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-based tracking…

Deep convolutional neural networks (CNNs) have made impressive progress in many video recognition tasks such as video pose estimation and video object detection. However, CNN inference on video is computationally expensive due to processing…

Visual tracking addresses the problem of identifying and localizing an unknown target in a video given the target specified by a bounding box in the first frame. In this paper, we propose a dual network to better utilize features among…

Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches to image analysis mostly process objects independently and do…

One-shot Video Object Segmentation~(VOS) is the task of pixel-wise tracking an object of interest within a video sequence, where the segmentation mask of the first frame is given at inference time. In recent years, Recurrent Neural…

We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception,…

Although deep learning based methods have achieved great progress in unsupervised video object segmentation, difficult scenarios (e.g., visual similarity, occlusions, and appearance changing) are still not well-handled. To alleviate these…