GitHub

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages

Abstract. An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop. When only a handful of samples are available per category, as ...
IEEE

Pedestrian Vision Language Model for Intentions Prediction

Abstract: Effective modeling of human behavior is crucial for the safe and reliable coexistence of humans and autonomous vehicles. Traditional deep learning methods have limitations in capturing the ...
marktechpost

Google Introduces T5Gemma 2: Encoder Decoder Models with Multimodal Inputs via SigLIP and 128K Context

T5Gemma 2 follows the same adaptation idea introduced in T5Gemma, initialize an encoder-decoder model from a decoder-only checkpoint, then adapt with UL2. In the above figure the research team show ...
IEEE

TJCMNet: An Efficient Vision-Text Joint Identity Clues Mining Network for Visible-Infrared Person Re-Identification

Abstract: Retrieving images for Visible-Infrared Person Re-identification task is challenging, because of the huge modality discrepancy caused by the different imaging principle of RGB and infrared ...