Related papers: Exploring Optical-Flow-Guided Motion and Detection…
3D visual grounding aims to automatically locate the 3D region of the specified object given the corresponding textual description. Existing works fail to distinguish similar objects especially when multiple referred objects are involved in…
Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications. State-of-the-art recurrent neural networks (RNN) based models map an input…
Enabling intelligent agents to comprehend and interact with 3D environments through natural language is crucial for advancing robotics and human-computer interaction. A fundamental task in this field is ego-centric 3D visual grounding,…
Sequential grounding in 3D point clouds (SG3D) refers to locating sequences of objects by following text instructions for a daily activity with detailed steps. Current 3D visual grounding (3DVG) methods treat text instructions with multiple…
Temporal Video Grounding (TVG) aims to localize temporal moments in an untrimmed video that semantically correspond to given natural language queries. Recently, Graph Convolutional Networks (GCN) have been widely adopted in TVG to model…
Interpreting motion captured in image sequences is crucial for a wide range of computer vision applications. Typical estimation approaches include optical flow (OF), which approximates the apparent motion instantaneously in a scene, and…
Estimating accurate camera poses, 3D scene geometry, and object motion from in-the-wild videos is a long-standing challenge for classical structure from motion pipelines due to the presence of dynamic objects. Recent learning-based methods…
Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences, enabling bidirectional search across the two modalities. Most existing methods use a…
A novel framework named Markov Clustering Network (MCN) is proposed for fast and robust scene text detection. MCN predicts instance-level bounding boxes by firstly converting an image into a Stochastic Flow Graph (SFG) and then performing…
In autonomous driving, LiDAR sensors are vital for acquiring 3D point clouds, providing reliable geometric information. However, traditional sampling methods of preprocessing often ignore semantic features, leading to detail loss and ground…
Although great progress has been made in 3D visual grounding, current models still rely on explicit textual descriptions for grounding and lack the ability to reason human intentions from implicit instructions. We propose a new task called…
Vision-and-language navigation requires an agent to navigate through a real 3D environment following natural language instructions. Despite significant advances, few previous works are able to fully utilize the strong correspondence between…
Affordance reasoning in 3D Gaussian scenes aims to identify the region that supports the action specified by a given text instruction in complex environments. Existing methods typically cast this problem as one-shot prediction from static…
Enabling robots to grasp objects specified through natural language is essential for effective human-robot interaction, yet it remains a significant challenge. Existing approaches often struggle with open-form language expressions and…
We develop a Deep-Text Recurrent Network (DTRN) that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered high-level sequence from a whole word…
Multi-modal language models (LM) have recently shown promising performance in high-level reasoning tasks on videos. However, existing methods still fall short in tasks like causal or compositional spatiotemporal reasoning over actions, in…
Fully convolutional neural networks (FCNNs) trained on a large number of images with strong pixel-level annotations have become the new state of the art for the semantic segmentation task. While there have been recent attempts to learn…
We propose a Spatiotemporal Sampling Network (STSN) that uses deformable convolutions across time for object detection in videos. Our STSN performs object detection in a video frame by learning to spatially sample features from the adjacent…
Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved. For example, most of the previous methods model the representations of skeleton sequences without abundant spatial structure…
Recent advancements in foundation models for 2D vision have substantially improved the analysis of dynamic scenes from monocular videos. However, despite their strong generalization capabilities, these models often lack 3D consistency, a…