Related papers: Balancing Stability and Plasticity in Pretrained D…
Deep-learning-based local feature extraction algorithms that combine detection and description have made significant progress in visible image matching. However, the end-to-end training of such frameworks is notoriously unstable due to the…
Fine-grained medical image classification is challenged by subtle inter-class variations and visually ambiguous cases, where confidence estimates often exhibit uncertainty rather than being overconfident. In such scenarios, purely…
Segmentation and tracking of unseen object instances in discrete frames pose a significant challenge in dynamic industrial robotic contexts, such as distribution warehouses. Here, robots must handle object rearrangement, including shifting,…
Multispectral pedestrian detection is an important task for many around-the-clock applications, since the visible and thermal modalities can provide complementary information especially under low light conditions. Due to the presence of two…
One of the main reasons for topological persistence being useful in data analysis is that it is backed up by a stability (isometry) property: persistence diagrams of $1$-parameter persistence modules are stable in the sense that the…
We consider multitarget detection and tracking problem for a class of multipath detection system where one target may generate multiple measurements via multiple propagation paths, and the association relationship among targets,…
The tracking-by-detection paradigm is the mainstream in multi-object tracking, associating tracks to the predictions of an object detector. Although exhibiting uncertainty through a confidence score, these predictions do not capture the…
Reconstruction-based anomaly detection models achieve their purpose by suppressing the generalization ability for anomaly. However, diverse normal patterns are consequently not well reconstructed as well. Although some efforts have been…
We develop a new method to isolate localized defects from extended vibrational modes in disordered solids. This method augments particle interactions with an artificial potential that acts as a high-pass filter: it preserves small-scale…
Deep learning models such as convolutional neural networks and transformers have been widely applied to solve 3D object detection problems in the domain of autonomous driving. While existing models have achieved outstanding performance on…
Material discovery is a cornerstone of modern science, driving advancements in diverse disciplines from biomedical technology to climate solutions. Predicting synthesizability, a critical factor in realizing novel materials, remains a…
Detecting the openable parts of articulated objects is crucial for downstream applications in intelligent robotics, such as pulling a drawer. This task poses a multitasking challenge due to the necessity of understanding object categories…
Head detection and tracking are essential for downstream tasks, but current methods often require large computational budgets, which increase latencies and ties up resources (e.g., processors, memory, and bandwidth). To address this, we…
A robust $hp$-adaptive finite element framework is presented for the investigation of static cracks in materials characterized by complex, pointwise density variations. Within such heterogeneous media, the equilibrium equation governed by…
3D object detection is essential in autonomous driving, providing vital information about moving objects and obstacles. Detecting objects in distant regions with only a few LiDAR points is still a challenge, and numerous strategies have…
Multimodal learning, particularly for pedestrian detection, has recently received emphasis due to its capability to function equally well in several critical autonomous driving scenarios such as low-light, night-time, and adverse weather…
Object modeling has become a core part of recent tracking frameworks. Current popular tackers use Transformer attention to extract the template feature separately or interactively with the search region. However, separate template learning…
Recent advances in generative AI have dramatically improved photorealistic image synthesis, yet they fall short for studio-level multi-object compositing. This task demands simultaneous (i) near-perfect preservation of each item's identity,…
We propose ProTracker, a novel framework for accurate and robust long-term dense tracking of arbitrary points in videos. Previous methods relying on global cost volumes effectively handle large occlusions and scene changes but lack…
Adapting pretrained multi-modal models to evolving test-time distributions, known as multi-modal test-time adaptation, presents a significant challenge. Existing methods frequently encounter negative transfer in the unbiased modality and…