activity
20122024
most citedPSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences

69 citations · 382 across the 33 of their papers we have counts for

collaborators
Showing cs.CVShow all

27 papers · 1 filter

cs.CV2024

Joint Vision-Language Social Bias Removal for CLIP

Haoyu Zhang, Yangyang Guo, Mohan Kankanhalli

Vision-Language (V-L) pre-trained models such as CLIP show prominent capabilities in various downstream tasks. Despite this promise, V-L models are notoriously limited by their inh…

cs.CV2024

SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency

Yangyang Guo, Mohan Kankanhalli

While contrastive pre-training is widely employed, its data efficiency problem has remained relatively under-explored thus far. Existing methods often rely on static coreset select…

cs.CV2024

VidHal: Benchmarking Temporal Hallucinations in Vision LLMs

Wey Yeh Choong, Yangyang Guo, Mohan Kankanhalli

Vision Large Language Models (VLLMs) are widely acknowledged to be prone to hallucinations. Existing research addressing this problem has primarily been confined to image inputs, w…

cs.CV20229 cited

Effective Abstract Reasoning with Dual-Contrast Network

Tao Zhuo, Mohan Kankanhalli

As a step towards improving the abstract reasoning capability of machines, we aim to solve Raven's Progressive Matrices (RPM) with neural networks, since solving RPM puzzles is hig…

cs.CV202269 cited

PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences

Hehe Fan, Xin Yu, Yuhang Ding +2

Point cloud sequences are irregular and unordered in the spatial dimension while exhibiting regularities and order in the temporal dimension. Therefore, existing grid based convolu…

cs.CV20214 cited

Learning to Predict Trustworthiness with Steep Slope Loss

Yan Luo, Yongkang Wong, Mohan S. Kankanhalli +1

Understanding the trustworthiness of a prediction yielded by a classifier is critical for the safe and effective use of AI models. Prior efforts have been proven to be reliable on…