3 citations · 4 across the 24 of their papers we have counts for
14 papers · 1 filter
VETO: Video Efficient Token Optimization for Vision Language Models
Gueter Josmy Faure, Hao Ping Wang, Min-Hung Chen +1
Processing long videos with Vision-Language Models (VLMs) is bottlenecked by the quadratic cost of visual tokens, making long-form inference prohibitively expensive. While single-a…
ActionLens: Diagnosing Spatial-Temporal Binding Failures in Vision-Language Models
Gueter Josmy Faure, Min-Hung Chen, Hao Ping Wang +3
Video-capable vision-language models score above 80\% on popular benchmarks yet struggle with spatial-temporal binding: associating the right action with the right person at the ri…
FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding
Gueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh +2
Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for real…
SPATIOROUTE: Dynamic Prompt Routing for Zero-Shot Spatial Reasoning
Pawat Chunhachatrachai, Gueter Josmy Faure, Hung-Ting Su +1
Spatial question answering over egocentric video is a challenging task that requires Vision-Language Models (VLMs) to reason about 3D object positions, scene affordances, and direc…
SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization
Posheng Chen, Powen Cheng, Gueter Josmy Faure +2
In real-world scenes, target objects may reside in regions that are not visible. While humans can often infer the locations of occluded objects from context and commonsense knowled…
Improving Generalization Ability for 3D Object Detection by Learning Sparsity-invariant Features
Hsin-Cheng Lu, Chung-Yi Lin, Winston H. Hsu
In autonomous driving, 3D object detection is essential for accurately identifying and tracking objects. Despite the continuous development of various technologies for this task, a…
Leveraging Content and Context Cues for Low-Light Image Enhancement
Igor Morawski, Kai He, Shusil Dangi +1
Low-light conditions have an adverse impact on machine cognition, limiting the performance of computer vision systems in real life. Since low-light data is limited and difficult to…
Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection
Huang-Yu Chen, Jia-Fong Yeh, Jia-Wei Liao +2
LiDAR-based 3D object detection is a critical technology for the development of autonomous driving and robotics. However, the high cost of data annotation limits its advancement. W…
HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics
Gueter Josmy Faure, Jia-Fong Yeh, Min-Hung Chen +3
Long-form video understanding presents unique challenges that extend beyond traditional short-video analysis approaches, particularly in capturing long-range dependencies, processi…
Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies
Hung-Ting Su, Chun-Tong Chao, Ya-Ching Hsu +4
Large Language Models (LLMs) have demonstrated effectiveness not only in language tasks but also in video reasoning. This paper introduces a novel dataset, Tropes in Movies (TiM),…
Unsupervised Image Prior via Prompt Learning and CLIP Semantic Guidance for Low-Light Image Enhancement
Igor Morawski, Kai He, Shusil Dangi +1
Currently, low-light conditions present a significant challenge for machine cognition. In this paper, rather than optimizing models by assuming that human and machine cognition are…
Tel2Veh: Fusion of Telecom Data and Vehicle Flow to Predict Camera-Free Traffic via a Spatio-Temporal Framework
ChungYi Lin, Shen-Lung Tung, Hung-Ting Su +1
Vehicle flow, a crucial indicator for transportation, is often limited by detector coverage. With the advent of extensive mobile network coverage, we can leverage mobile user activ…
Tracking-Assisted Object Detection with Event Cameras
Ting-Kang Yen, Igor Morawski, Shusil Dangi +5
Event-based object detection has recently garnered attention in the computer vision community due to the exceptional properties of event cameras, such as high dynamic range and no…
WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
Tsung-Lin Tsou, Tsung-Han Wu, Winston H. Hsu
In the field of domain adaptation (DA) on 3D object detection, most of the work is dedicated to unsupervised domain adaptation (UDA). Yet, without any target annotations, the perfo…