Related papers: MoLo: Motion-augmented Long-short Contrastive Lear…
We study multi-modal few-shot object detection (FSOD) in this paper, using both few-shot visual examples and class semantic information for detection, which are complementary to each other by definition. Most of the previous works on…
The design of deep learning methods for low light video enhancement remains a challenging problem owing to the difficulty in capturing low light and ground truth video pairs. This is particularly hard in the context of dynamic scenes or…
Understanding human behavior is an important problem in the pursuit of visual intelligence. A challenge in this endeavor is the extensive and costly effort required to accurately label action segments. To address this issue, we consider…
Radar for deep learning-based human identification has become a research area of increasing interest. It has been shown that micro-Doppler ($\mu$-D) can reflect the walking behavior through capturing the periodic limbs' micro-motions. One…
Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…
Sign language recognition from sequences of monocular images or 2D poses is a challenging field, not only due to the difficulty to infer 3D information from 2D data, but also due to the temporal relationship between the sequences of…
Reinforcement Learning (RL) has demonstrated remarkable success in solving sequential decision-making problems. However, in real-world scenarios, RL agents often struggle to generalize when faced with unseen actions that were not…
Few-shot object detection aims to detect instances of specific categories in a query image with only a handful of support samples. Although this takes less effort than obtaining enough annotated images for supervised object detection, it…
Due to the scarcity of sampling data in reality, few-shot object detection (FSOD) has drawn more and more attention because of its ability to quickly train new detection concepts with less data. However, there are still failure…
In this work, we address the challenging task of few-shot segmentation. Previous few-shot segmentation methods mainly employ the information of support images as guidance for query image segmentation. Although some works propose to build…
Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…
Pre-trained vision language models have shown remarkable performance on visual recognition tasks, but they typically assume the availability of complete multimodal inputs during both training and inference. In real-world scenarios, however,…
Few-shot action recognition aims to address the high cost and impracticality of manually labeling complex and variable video data in action recognition. It requires accurately classifying human actions in videos using only a few labeled…
We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged encoder. This enables…
Multi-modal Large Language Models (MLLMs) struggle with long videos due to the need for excessive visual tokens. These tokens exceed massively the context length of MLLMs, resulting in filled by redundant task-irrelevant shots. How to…
Multi-modal contrastive learning with language supervision has presented a paradigm shift in modern machine learning. By pre-training on a web-scale dataset, multi-modal contrastive learning can learn high-quality representations that…
Vision-language models (VLMs) pre-trained on natural image and language data, such as CLIP, have exhibited significant potential in few-shot image recognition tasks, leading to development of various efficient transfer learning methods.…
Few-shot learning (FSL) aims to learn novel visual categories from very few samples, which is a challenging problem in real-world applications. Many methods of few-shot classification work well on general images to learn global…
Continual learning allows a model to learn multiple tasks sequentially while retaining the old knowledge without the training data of the preceding tasks. This paper extends the scope of continual learning research to class-incremental…
While vision-language-action (VLA) models have advanced generalist robotic learning, cross-embodiment transfer remains challenging due to kinematic heterogeneity and the high cost of collecting sufficient real-world demonstrations to…