Related papers: Transfer Learning for Keypoint Detection in Low-Re…

The success of large-scale pre-trained models has established fine-tuning as a standard method for achieving significant improvements in downstream tasks. However, fine-tuning the entire parameter set of a pre-trained model is costly.…

Knee osteoporosis weakens the bone tissue in the knee joint, increasing fracture risk. Early detection through X-ray images enables timely intervention and improved patient outcomes. While some researchers have focused on diagnosing knee…

Deep learning and reinforcement learning methods have been shown to enable learning of flexible and complex robot controllers. However, the reliance on large amounts of training data often requires data collection to be carried out in…

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and…

Identifying thermodynamic signatures of electronic phases, such as superconductivity, is challenging in low-dimensional materials due to strong fluctuations and low probing volume. Spectroscopic methods are often used to identify new bulk…

Transportation systems often rely on understanding the flow of vehicles or pedestrian. From traffic monitoring at the city scale, to commuters in train terminals, recent progress in sensing technology make it possible to use cameras to…

Uncertainty estimation is at the core of Active Learning (AL). Most existing methods resort to complex auxiliary models and advanced training fashions to estimate uncertainty for unlabeled data. These models need special design and hence…

Recently, occluded person re-identification(Re-ID) remains a challenging task that people are frequently obscured by other people or obstacles, especially in a crowd massing situation. In this paper, we propose a self-supervised deep…

Transformers have recently been shown to generate high quality images from text input. However, the existing method of pose conditioning using skeleton image tokens is computationally inefficient and generate low quality images. Therefore…

In this paper, we are interested in the bottom-up paradigm of estimating human poses from an image. We study the dense keypoint regression framework that is previously inferior to the keypoint detection and grouping framework. Our…

Short video has witnessed rapid growth in the past few years in e-commerce platforms like Taobao. To ensure the freshness of the content, platforms need to release a large number of new videos every day, making conventional click-through…

Keypoint detection and tracking in traditional image frames are often compromised by image quality issues such as motion blur and extreme lighting conditions. Event cameras offer potential solutions to these challenges by virtue of their…

In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…

This study investigates the classification of aerial images depicting transmission towers, forests, farmland, and mountains. To complete the classification job, features are extracted from input photos using a Convolutional Neural Network…

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of…

Occupancy plays an essential role in influencing the energy consumption and operation of heating, ventilation, and air conditioning (HVAC) systems. Traditional HVAC typically operate on fixed schedules without considering occupancy.…

This work addresses the challenge of sub-pixel accuracy in detecting 2D local features, a cornerstone problem in computer vision. Despite the advancements brought by neural network-based methods like SuperPoint and ALIKED, these modern…

Denoising diffusion probabilistic models that were initially proposed for realistic image generation have recently shown success in various perception tasks (e.g., object detection and image segmentation) and are increasingly gaining…

Gesture recognition using low-resolution instantaneous HD-sEMG images opens up new avenues for the development of more fluid and natural muscle-computer interfaces. However, the data variability between inter-session and inter-subject…

Semi-supervised video object segmentation (semi-VOS) is widely used in many applications. This task is tracking class-agnostic objects from a given target mask. For doing this, various approaches have been developed based on…