Few-shot backdoor defense using shapley estimation
Deep neural networks have achieved impressive performance in a variety of tasks over the
last decade, such as autonomous driving, face recognition, and medical diagnosis …
last decade, such as autonomous driving, face recognition, and medical diagnosis …
Exploring feature compensation and cross-level correlation for infrared small target detection
Single frame infrared small target (SIRST) detection is useful for many practical applications,
such as maritime rescue. However, SIRST detection is challenging due to the low-contrast …
such as maritime rescue. However, SIRST detection is challenging due to the low-contrast …
Towards scale-aware, robust, and generalizable unsupervised monocular depth estimation by integrating IMU motion dynamics
Unsupervised monocular depth and ego-motion estimation has drawn extensive research
attention in recent years. Although current methods have reached a high up-to-scale …
attention in recent years. Although current methods have reached a high up-to-scale …
Vitpose++: Vision transformer for generic body pose estimation
In this paper, we show the surprisingly good properties of plain vision transformers for body
pose estimation from various aspects, namely simplicity in model structure, scalability in …
pose estimation from various aspects, namely simplicity in model structure, scalability in …
EdgeAdaptor: Online configuration adaption, model selection and resource provisioning for edge DNN inference serving at scale
The accelerating convergence of artificial intelligence and edge computing has sparked a
recent wave of interest in edge intelligence. While pilot efforts focused on edge DNN …
recent wave of interest in edge intelligence. While pilot efforts focused on edge DNN …
Ferroelectric nitride heterostructures on CMOS compatible molybdenum for synaptic memristors
Achieving ferroelectricity in III-nitride (III-N) semiconductors by alloying with rare-earth
elements, eg, scandium, has presented a pivotal step toward next-generation electronic …
elements, eg, scandium, has presented a pivotal step toward next-generation electronic …
Smart liquid-piston based triboelectric nanogenerator sensor for real-time monitoring of fluid status
It is highly desirable to measure fluid pressure and its pulsations through portable, handheld
instruments and test kits, which allow a rapid, low-cost, and reliable quantification about …
instruments and test kits, which allow a rapid, low-cost, and reliable quantification about …
Apt-36k: A large-scale benchmark for animal pose estimation and tracking
Animal pose estimation and tracking (APT) is a fundamental task for detecting and tracking
animal keypoints from a sequence of video frames. Previous animal-related datasets focus …
animal keypoints from a sequence of video frames. Previous animal-related datasets focus …
Glt-t: Global-local transformer voting for 3d single object tracking in point clouds
Current 3D single object tracking methods are typically based on VoteNet, a 3D region
proposal network. Despite the success, using a single seed point feature as the cue for offset …
proposal network. Despite the success, using a single seed point feature as the cue for offset …
Brain-inspired cognitive model with attention for self-driving cars
The perception-driven approach and end-to-end system are two major vision-based
frameworks for self-driving cars. However, it is difficult to introduce attention and historical …
frameworks for self-driving cars. However, it is difficult to introduce attention and historical …