Object detection as a subfield within computer vision has achieved remarkable progress,
which aims to accurately identify and locate a specific object from images or videos. Such …

Abstract Vision-Language Pre-training (VLP) models have shown promising capabilities in
grounding natural language in image data, facilitating a broad range of cross-modal tasks …

Few-shot object detection (FSOD), with the aim to detect novel objects using very few
training examples, has recently attracted great research interest in the community. Metric …

Generalized few-shot object detection aims to achieve precise detection on both base
classes with abundant annotations and novel classes with limited training data. Existing …

Few-shot object detection (FSOD) aims to detect objects using only a few examples. How to
adapt state-of-the-art object detectors to the few-shot domain remains challenging. Object …

Abstract Vision Transformers (ViTs) emerge to achieve impressive performance on many
data-abundant computer vision tasks by capturing long-range dependencies among local …

Few-shot object detection (FSOD) aims to detect objects with only a few training examples.
Visual feature extraction and query-support similarity learning are the two critical …

Existing temporal action detection (TAD) methods rely on large training data including
segment-level annotations, limited to recognizing previously seen classes alone during …

Object detection has achieved a huge breakthrough with deep neural networks and massive
annotated data. However, current detection methods cannot be directly transferred to the …

There are still two problems in SDD causing some inaccurate results:(1) In the process of
feature extraction, with the layer-by-layer acquisition of semantic information, local …