1 citations · 5 across the 34 of their papers we have counts for
28 papers · 1 filter
XLocalizer: Cross-grained Alignment for Progressive Cross-view Video Geo-localization
Zichao Zeng, Weijia Fan, Yufan Chen +7
Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images. However, CVG approaches rely on fixed-length…
SeqLoc: Beyond the Single Frame for Cross-View Geo-Localization in Feature-Sparse Scenes
Junwei Zheng, Yun Huang, Ruize Dai +8
Cross-View Geo-Localization (CVGL) with OpenStreetMap (OSM) performs well in structure-rich urban environments but collapses in feature-sparse scenes such as rural roads. To study…
Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning
Zichao Zeng, June Moh Goo, Junwei Zheng +4
Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art methods employ Vision Transforme…
TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT
Marawan Elbatel, Mohamed Ghonim, Jiaji Mao +62
Automated segmentation of liver lesions on non-contrast computed tomography (NCCT) is clinically important but fundamentally challenging, particularly in low-resource settings acro…
IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning
Qian Yin, Di Wen, Kunyu Peng +11
Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correcti…
IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction
Haoshen Zhang, Di Wen, Kunyu Peng +12
We present IMPACT-HOI, a mixed-initiative framework for annotating egocentric procedural video by constructing structured event graphs for Human-Object Interactions (HOI), motivate…
EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos
Ruiping Liu, Junwei Zheng, Yufan Chen +7
Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and obs…
IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory
Weitong Kong, Di Wen, Kunyu Peng +10
Correcting errors in long-video understanding is disproportionately costly: existing multimodal pipelines produce opaque, end-to-end outputs that expose no intermediate state for i…
IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly
Di Wen, Zeyun Zhong, David Schneider +18
We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial…
More than the Sum: Panorama-Language Models for Adverse Omni-Scenes
Weijia Fan, Ruiping Liu, Jiale Wei +7
Existing vision-language models (VLMs) are tailored for pinhole imagery, stitching multiple narrow field-of-view inputs to piece together a complete omni-scene understanding. Yet,…
SGR3 Model: Scene Graph Retrieval-Reasoning Model in 3D
Zirui Wang, Ruiping Liu, Yufan Chen +7
3D scene graphs provide a structured representation of object entities and their relationships, enabling high-level interpretation and reasoning for robots while remaining intuitiv…
RHO: Robust Holistic OSM-Based Metric Cross-View Geo-Localization
Junwei Zheng, Ruize Dai, Ruiping Liu +7
Metric Cross-View Geo-Localization (MCVGL) aims to estimate the 3-DoF camera pose (position and heading) by matching ground and satellite images. In this work, instead of pinhole a…
What if? Emulative Simulation with World Models for Situated Reasoning
Ruiping Liu, Yufan Chen, Yuheng Zhang +8
Situated reasoning often relies on active exploration, yet in many real-world scenarios such exploration is infeasible due to physical constraints of robots or safety concerns of v…
HybriDLA: Hybrid Generation for Document Layout Analysis
Yufan Chen, Omar Moured, Ruiping Liu +4
Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for ea…
mmWalk: Towards Multi-modal Multi-view Walking Assistance
Kedi Ying, Ruiping Liu, Chongyan Chen +5
Walking assistance in extreme or complex environments remains a significant challenge for people with blindness or low vision (BLV), largely due to the lack of a holistic scene und…
RefAtomNet++: Advancing Referring Atomic Video Action Recognition using Multi-Trajectory Semantic Retrieval
Kunyu Peng, Di Wen, Jia Fu +9
Who is being described, where are they, and what are they doing? Referring Atomic Video Action Recognition (RAVAR) answers these questions jointly by grounding a natural-language r…
EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
Kunyu Peng, Di Wen, Kailun Yang +9
Open-Set Domain Generalization (OSDG) aims to enable deep learning models to recognize unseen categories in new domains, which is crucial for real-world applications. Label noise h…
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
Ruiping Liu, Junwei Zheng, Yufan Chen +6
Physical environments and circumstances are fundamentally dynamic, yet current 3D datasets and evaluation benchmarks tend to concentrate on either dynamic scenarios or dynamic situ…
Exploring Single Domain Generalization of LiDAR-based Semantic Segmentation under Imperfect Labels
Weitong Kong, Zichao Zeng, Di Wen +5
Accurate perception is critical for vehicle safety, with LiDAR as a key enabler in autonomous driving. To ensure robust performance across environments, sensor types, and weather c…
RoHOI: Robustness Benchmark for Human-Object Interaction Detection
Di Wen, Kunyu Peng, Kailun Yang +7
Human-Object Interaction (HOI) detection is crucial for robot-human assistance, enabling context-aware support. However, models trained on clean datasets degrade in real-world cond…
HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
Kunyu Peng, Junchao Huang, Xiangsheng Huang +7
Action segmentation is a core challenge in high-level video understanding, aiming to partition untrimmed videos into segments and assign each a label from a predefined action set.…
Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments
Di Wen, Lei Qi, Kunyu Peng +9
Despite substantial progress in video understanding, most existing datasets are limited to Earth's gravitational conditions. However, microgravity alters human motion, interactions…
Exploring Video-Based Driver Activity Recognition under Noisy Labels
Linjuan Fan, Di Wen, Kunyu Peng +8
As an open research topic in the field of deep learning, learning with noisy labels has attracted much attention and grown rapidly over the past ten years. Learning with label nois…
Graph-based Document Structure Analysis
Yufan Chen, Ruiping Liu, Junwei Zheng +4
When reading a document, glancing at the spatial layout of a document is an initial step to understand it roughly. Traditional document layout analysis (DLA) methods, however, offe…