3 citations · 4 across the 24 of their papers we have counts for
27 papers
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…
ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints
Pei-An Chen, Yong-Ching Liang, Jia-Fong Yeh +4
Intelligent embodied agents should not simply follow instructions, as real-world environments often involve unexpected conditions and exceptions. However, existing methods usually…
VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructions
Hung-Ting Su, Ting-Jun Wang, Jia-Fong Yeh +2
Conventional Vision-and-Language Navigation (VLN) benchmarks assume instructions are feasible and the referenced target exists, leaving agents ill-equipped to handle false-premise…
Affordance-Guided Coarse-to-Fine Exploration for Base Placement in Open-Vocabulary Mobile Manipulation
Tzu-Jung Lin, Jia-Fong Yeh, Hung-Ting Su +3
In open-vocabulary mobile manipulation (OVMM), task success often hinges on the selection of an appropriate base placement for the robot. Existing approaches typically navigate to…
MovieCORE: COgnitive REasoning in Movies
Gueter Josmy Faure, Min-Hung Chen, Jia-Fong Yeh +5
This paper introduces MovieCORE, a novel video question answering (VQA) dataset designed to probe deeper cognitive understanding of movie content. Unlike existing datasets that foc…
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…
Context-Aware Replanning with Pre-explored Semantic Map for Object Navigation
Po-Chen Ko, Hung-Ting Su, Ching-Yuan Chen +3
Pre-explored Semantic Maps, constructed through prior exploration using visual language models (VLMs), have proven effective as foundational elements for training-free robotic appl…
Attention Tracker: Detecting Prompt Injection Attacks in LLMs
Kuo-Han Hung, Ching-Yun Ko, Ambrish Rawat +3
Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring origin…
Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses
Hung-Ting Su, Ya-Ching Hsu, Xudong Lin +5
Large language models (LLMs) equipped with chain-of-thoughts (CoT) prompting have shown significant multi-step reasoning capabilities in factual content like mathematics, commonsen…
Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation
Tsung-Han Wu, Hung-Ting Su, Shang-Tse Chen +1
The robust self-training (RST) framework has emerged as a prominent approach for semi-supervised adversarial training. To explore the possibility of tackling more complicated tasks…
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),…
Shared-unique Features and Task-aware Prioritized Sampling on Multi-task Reinforcement Learning
Po-Shao Lin, Jia-Fong Yeh, Yi-Ting Chen +1
We observe that current state-of-the-art (SOTA) methods suffer from the performance imbalance issue when performing multi-task reinforcement learning (MTRL) tasks. While these meth…
Enhancing Sustainable Urban Mobility Prediction with Telecom Data: A Spatio-Temporal Framework Approach
ChungYi Lin, Shen-Lung Tung, Hung-Ting Su +1
Traditional traffic prediction, limited by the scope of sensor data, falls short in comprehensive traffic management. Mobile networks offer a promising alternative using network ac…
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…
VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation
Kuo-Han Hung, Pang-Chi Lo, Jia-Fong Yeh +3
We study reward models for long-horizon manipulation tasks by learning from action-free videos and language instructions, which we term the visual-instruction correlation (VIC) pro…
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…