3 citations · 10 across the 17 of their papers we have counts for
19 papers
Continual-NExT: A Unified Comprehension And Generation Continual Learning Framework
Jingyang Qiao, Zhizhong Zhang, Xin Tan +3
Dual-to-Dual MLLMs refer to Multimodal Large Language Models, which can enable unified multimodal comprehension and generation through text and image modalities. Although exhibitin…
Vision-language models lag human performance on physical dynamics and intent reasoning
Tianjun Gu, Jingyu Gong, Zhizhong Zhang +4
Spatial intelligence is central to embodied cognition, yet contemporary AI systems still struggle to reason about physical interactions in open-world human environments. Despite st…
PFDepth: Heterogeneous Pinhole-Fisheye Joint Depth Estimation via Distortion-aware Gaussian-Splatted Volumetric Fusion
Zhiwei Zhang, Ruikai Xu, Weijian Zhang +5
In this paper, we present the first pinhole-fisheye framework for heterogeneous multi-view depth estimation, PFDepth. Our key insight is to exploit the complementary characteristic…
T2S: Tokenized Skill Scaling for Lifelong Imitation Learning
Hongquan Zhang, Jingyu Gong, Zhizhong Zhang +3
The main challenge in lifelong imitation learning lies in the balance between mitigating catastrophic forgetting of previous skills while maintaining sufficient capacity for acquir…
NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks
Zhihao Luo, Wentao Yan, Jingyu Gong +5
Recent advances in Graphical User Interface (GUI) and embodied navigation have driven progress, yet these domains have largely evolved in isolation, with disparate datasets and tra…
UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images
Qijian Tian, Xin Tan, Jingyu Gong +2
We propose a feed-forward Gaussian Splatting model that unifies 3D scene and semantic field reconstruction. Combining 3D scenes with semantic fields facilitates the perception and…
YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos
Haoming Chen, Lichen Yuan, TianFang Sun +5
3D semantic occupancy prediction is crucial for fine-grained scene understanding, yet its advancement in privacy-sensitive indoor environments is fundamentally hindered by the scar…
DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation
Tianjun Gu, Linfeng Li, Xuhong Wang +6
Adaptive navigation in unfamiliar environments is crucial for household service robots but remains challenging due to the need for both low-level path planning and high-level scene…
Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions
Boran Wen, Dingbang Huang, Zichen Zhang +6
Reconstructing human-object interactions (HOI) from single images is fundamental in computer vision. Existing methods are primarily trained and tested on indoor scenes due to the l…
DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion
Yinghui Li, Qianyu Zhou, Jingyu Gong +4
Point Transformers (PoinTr) have shown great potential in point cloud completion recently. Nevertheless, effective domain adaptation that improves transferability toward target dom…
Diffusion Implicit Policy for Unpaired Scene-aware Motion Synthesis
Jingyu Gong, Chong Zhang, Fengqi Liu +5
Scene-aware motion synthesis has been widely researched recently due to its numerous applications. Prevailing methods rely heavily on paired motion-scene data, while it is difficul…
Textual Decomposition Then Sub-motion-space Scattering for Open-Vocabulary Motion Generation
Ke Fan, Jiangning Zhang, Ran Yi +6
Text-to-motion generation is a crucial task in computer vision, which generates the target 3D motion by the given text. The existing annotated datasets are limited in scale, result…
Emphasizing Semantic Consistency of Salient Posture for Speech-Driven Gesture Generation
Fengqi Liu, Hexiang Wang, Jingyu Gong +5
Speech-driven gesture generation aims at synthesizing a gesture sequence synchronized with the input speech signal. Previous methods leverage neural networks to directly map a comp…
FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis
Ke Fan, Junshu Tang, Weijian Cao +7
Text-to-motion synthesis is a crucial task in computer vision. Existing methods are limited in their universality, as they are tailored for single-person or two-person scenarios an…
DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perception
Jingyu Gong, Min Wang, Wentao Liu +4
Motion synthesis in real-world 3D scenes has recently attracted much attention. However, the static environment assumption made by most current methods usually cannot be satisfied…
Prototype-Aware Heterogeneous Task for Point Cloud Completion
Junshu Tang, Jiachen Xu, Jingyu Gong +3
Point cloud completion, which aims at recovering original shape information from partial point clouds, has attracted attention on 3D vision community. Existing methods usually succ…
Exploring Versatile Prior for Human Motion via Motion Frequency Guidance
Jiachen Xu, Min Wang, Jingyu Gong +4
Prior plays an important role in providing the plausible constraint on human motion. Previous works design motion priors following a variety of paradigms under different circumstan…
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
Jingyu Gong, Jiachen Xu, Xin Tan +4
Hidden features in neural network usually fail to learn informative representation for 3D segmentation as supervisions are only given on output prediction, while this can be solved…
SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor
Jiachen Xu, Jingyu Gong, Jie Zhou +3
Besides local features, global information plays an essential role in semantic segmentation, while recent works usually fail to explicitly extract the meaningful global information…