Related papers: Transformed ROIs for Capturing Visual Transformati…
Human-object interaction (HOI) detection as a downstream of object detection tasks requires localizing pairs of humans and objects and extracting the semantic relationships between humans and objects from an image. Recently, one-stage…
In recent years, a number of approaches based on 2D or 3D convolutional neural networks (CNN) have emerged for video action recognition, achieving state-of-the-art results on several large-scale benchmark datasets. In this paper, we carry…
In-context image editing aims to modify images based on a contextual sequence comprising text and previously generated images. Existing methods typically depend on task-specific pipelines and expert models (e.g., segmentation and…
Given an image and a natural language expression as input, the goal of referring image segmentation is to segment the foreground masks of the entities referred by the expression. Existing methods mainly focus on interactive learning between…
In recent years, video action recognition, as a fundamental task in the field of video understanding, has been deeply explored by numerous researchers.Most traditional video action recognition methods typically involve converting videos…
In this paper, we introduce Coarse-Fine Networks, a two-stream architecture which benefits from different abstractions of temporal resolution to learn better video representations for long-term motion. Traditional Video models process…
Scene understanding and object recognition is a difficult to achieve yet crucial skill for robots. Recently, Convolutional Neural Networks (CNN), have shown success in this task. However, there is still a gap between their performance on…
Video cameras are pervasively deployed in city scale for public good or community safety (i.e. traffic monitoring or suspected person tracking). However, analyzing large scale video feeds in real time is data intensive and poses severe…
Deep learning approaches have been established as the main methodology for video classification and recognition. Recently, 3-dimensional convolutions have been used to achieve state-of-the-art performance in many challenging video datasets.…
By integrating complementary information from RGB image and depth map, the ability of salient object detection (SOD) for complex and challenging scenes can be improved. In recent years, the important role of Convolutional Neural Networks…
Video action recognition, a critical problem in video understanding, has been gaining increasing attention. To identify actions induced by complex object-object interactions, we need to consider not only spatial relations among objects in a…
Temporal convolutions have been the paradigm of choice in action segmentation, which enhances long-term receptive fields by increasing convolution layers. However, high layers cause the loss of local information necessary for frame…
Extracting robust feature representation is one of the key challenges in object re-identification (ReID). Although convolution neural network (CNN)-based methods have achieved great success, they only process one local neighborhood at a…
Effective extraction of temporal patterns is crucial for the recognition of temporally varying actions in video. We argue that the fixed-sized spatio-temporal convolution kernels used in convolutional neural networks (CNNs) can be improved…
Visual tempo characterizes the dynamics and the temporal scale of an action. Modeling such visual tempos of different actions facilitates their recognition. Previous works often capture the visual tempo through sampling raw videos at…
Most RGB-based hand-object reconstruction methods rely on object templates, while template-free methods typically assume full object visibility. This assumption often breaks in real-world settings, where fixed camera viewpoints and static…
The ubiquity of monocular videos capturing daily hand-object interactions presents a valuable resource for embodied intelligence. While 3D hand reconstruction from in-the-wild videos has seen significant progress, reconstructing the…
In this paper, we propose an end-to-end 3D CNN for action detection and segmentation in videos. The proposed architecture is a unified deep network that is able to recognize and localize action based on 3D convolution features. A video is…
Learning-based methods to understand and model hand-object interactions (HOI) require a large amount of high-quality HOI data. One way to create HOI data is to transfer hand poses from a source object to another based on the objects'…
The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we…