Abstract Pretraining Vision Transformers (ViTs) has achieved great success in visual
recognition. A following scenario is to adapt a ViT to various image and video recognition …

ImageNet-1K serves as the primary dataset for pretraining deep learning models for
computer vision tasks. ImageNet-21K dataset, which is bigger and more diverse, is used …

Multi-label image recognition is a challenging computer vision task of practical use.
Progresses in this area, however, are often characterized by complicated methods, heavy …

Misinformation has become a pressing issue. Fake media, in both visual and textual forms,
is widespread on the web. While various deepfake detection and text fake news detection …

Tremendous progress has been made in recent years in developing better image captioning
models, yet most of them rely on a separate object detector to extract regional features …

In this paper, we introduce ML-Decoder, a new attention-based classification head. ML-
Decoder predicts the existence of class labels via queries, and enables better utilization of …

ImageNet has been the most popular image classification benchmark, but it is also the one
with a significant level of label noise. Recent studies have shown that many samples contain …

Document-level relation extraction aims to detect the relations within one document, which is
challenging since it requires complex reasoning using mentions, entities, local and global …

This paper presents a CLIP-based unsupervised learning method for annotation-free multi-
label image classification, including three stages: initialization, training, and inference. At the …

Multi-label classification (MLC) can attach multiple labels on single image, and has
achieved promising results on medical images. But existing MLC methods still face …