Abstract We present the Recognize Anything Model (RAM): a strong foundation model for
image tagging. RAM makes a substantial step for foundation models in computer vision …

Pretrained general-purpose language models can achieve state-of-the-art accuracies in
various natural language processing domains by adapting to downstream tasks via zero …

Comprehending the rich semantics in an image and ordering them in linguistic order are
essential to compose a visually-grounded and linguistically coherent description for image …

Solving multi-label recognition (MLR) for images in the low-label regime is a challenging
task with many real-world applications. Recent work learns an alignment between textual …

In label-noise learning, the noise transition matrix, bridging the class posterior for noisy and
clean data, has been widely exploited to learn statistically consistent classifiers. The …

Since the introduction of the Vision Transformer (ViT), researchers have sought to make ViTs
more efficient by removing redundant information in the processed tokens. While different …

The activations of Facial Action Units (AUs) mutually influence one another. While the
relationship between a pair of AUs can be complex and unique, existing approaches fail to …

Weakly supervised multi-label classification (WSML) task, which is to learn a multi-label
classification using partially observed labels per image, is becoming increasingly important …

Prompt tuning has been employed as an efficient way to adapt large vision-language pre-
trained models (eg CLIP) to various downstream tasks in data-limited or label-limited …

Sign languages are visual languages which convey information by signers' handshape,
facial expression, body movement, and so forth. Due to the inherent restriction of …