Related papers: MoLo: Motion-augmented Long-short Contrastive Lear…
Under the domain shift, cross-domain few-shot object detection aims to adapt object detectors in the target domain with a few annotated target data. There exists two significant challenges: (1) Highly insufficient target domain data; (2)…
Few-shot object detection (FSOD) aims to detect never-seen objects using few examples. This field sees recent improvement owing to the meta-learning techniques by learning how to match between the query image and few-shot class examples,…
Although vital to computer vision systems, few-shot action recognition is still not mature despite the wide research of few-shot image classification. Popular few-shot learning algorithms extract a transferable embedding from seen classes…
Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features. However, due to the local perception of the…
Few-shot image classification aims at training a model from only a few examples for each of the "novel" classes. This paper proposes the idea of associative alignment for leveraging part of the base data by aligning the novel training…
The application of activity recognition in the "AI + Education" field is gaining increasing attention. However, current work mainly focuses on the recognition of activities in manually captured videos and a limited number of activity types,…
Multi-object tracking (MOT) in human-dominant scenarios, which involves continuously tracking multiple people within video sequences, remains a significant challenge in computer vision due to targets' complex motion and severe occlusions.…
The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose.…
Predicting the neural response to natural images in the visual cortex requires extracting relevant features from the images and relating those feature to the observed responses. In this work, we optimize the feature extraction in order to…
Few-shot learning is a fundamental and challenging problem since it requires recognizing novel categories from only a few examples. The objects for recognition have multiple variants and can locate anywhere in images. Directly comparing…
Multi-Object Tracking (MOT) aims to detect and associate all desired objects across frames. Most methods accomplish the task by explicitly or implicitly leveraging strong cues (i.e., spatial and appearance information), which exhibit…
We introduce the task of weakly supervised learning for detecting human and object interactions in videos. Our task poses unique challenges as a system does not know what types of human-object interactions are present in a video or the…
The goal of few-shot learning is to classify unseen categories with few labeled samples. Recently, the low-level information metric-learning based methods have achieved satisfying performance, since local representations (LRs) are more…
When trained at sufficient scale, auto-regressive language models exhibit the notable ability to learn a new language task after being prompted with just a few examples. Here, we present a simple, yet effective, approach for transferring…
Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has…
Few-shot action recognition, i.e. recognizing new action classes given only a few examples, benefits from incorporating temporal information. Prior work either encodes such information in the representation itself and learns classifiers at…
Vision-language-action (VLA) models have shown remarkable capabilities in robotic manipulation, but their performance is sensitive to the $\textbf{action chunk length}$ used during training, termed $\textbf{horizon}$. Our empirical study…
Contrastive instance discrimination methods outperform supervised learning in downstream tasks such as image classification and object detection. However, these methods rely heavily on data augmentation during representation learning, which…
Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long…
The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP…