Related papers: 3DV: 3D Dynamic Voxel for Action Recognition in De…

During the last years, many advances have been made in tasks like3D model retrieval, 3D model classification, and 3D model segmentation.The typical 3D representations such as point clouds, voxels, and poly-gon meshes are mostly suitable for…

Recent advances in robot manipulation have leveraged pre-trained vision-language models (VLMs) and explored integrating 3D spatial signals into these models for effective action prediction, giving rise to the promising…

Existing multi-view three-dimensional (3D) object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones, being computationally complex. To address this problem, current…

Video action recognition, which is topical in computer vision and video analysis, aims to allocate a short video clip to a pre-defined category such as brushing hair or climbing stairs. Recent works focus on action recognition with deep…

Humans are remarkably flexible in understanding viewpoint changes due to visual cortex supporting the perception of 3D structure. In contrast, most of the computer vision models that learn visual representation from a pool of 2D images…

In this paper, we focus on the spatio-temporal aspect of recognizing Activities of Daily Living (ADL). ADL have two specific properties (i) subtle spatio-temporal patterns and (ii) similar visual patterns varying with time. Therefore, ADL…

Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both spatial and temporal domains poses significant…

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…

Recently, the popularity of depth-sensors such as Kinect has made depth videos easily available while its advantages have not been fully exploited. This paper investigates, for gesture recognition, to explore the spatial and temporal…

In the perception task of autonomous driving, multi-modal methods have become a trend due to the complementary characteristics of LiDAR point clouds and image data. However, the performance of multi-modal methods is usually limited by the…

Virtual content creation and interaction play an important role in modern 3D applications such as AR and VR. Recovering detailed 3D models from real scenes can significantly expand the scope of its applications and has been studied for…

Constructing photo-realistic Free-Viewpoint Videos (FVVs) of dynamic scenes from multi-view videos remains a challenging endeavor. Despite the remarkable advancements achieved by current neural rendering techniques, these methods generally…

In this work, we present a novel data-driven method for robust 6DoF object pose estimation from a single RGBD image. Unlike previous methods that directly regressing pose parameters, we tackle this challenging task with a keypoint-based…

We address the problem of 3D object detection, that is, estimating 3D object bounding boxes from point clouds. 3D object detection methods exploit either voxel-based or point-based features to represent 3D objects in a scene. Voxel-based…

Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain priors. This keeps the field isolated from the broader Transformer ecosystem, limiting…

Open-vocabulary 3D Object Detection (OV-3DDet) addresses the detection of objects from an arbitrary list of novel categories in 3D scenes, which remains a very challenging problem. In this work, we propose CoDAv2, a unified framework…

In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis. To this end, we propose DeepVoxels, a learned representation that encodes the…

Deep neural networks have achieved remarkable success for video-based action recognition. However, most of existing approaches cannot be deployed in practice due to the high computational cost. To address this challenge, we propose a new…

Multi-view projection methods have demonstrated promising performance on 3D understanding tasks like 3D classification and segmentation. However, it remains unclear how to combine such multi-view methods with the widely available 3D point…

We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficiently capture large…