Related papers: Gaze into the Pattern: Characterizing Spatial Patt…
Prefetching web pages is a well-studied solution to reduce network latency by predicting users' future actions based on their past behaviors. However, such techniques are largely unexplored on mobile platforms. Today's privacy regulations…
Gait recognition is one of the most critical long-distance identification technologies and increasingly gains popularity in both research and industry communities. Despite the significant progress made in indoor datasets, much evidence…
Gaze tracking is a useful human-to-computer interface, which plays an increasingly important role in a range of mobile applications. Gaze calibration is an indispensable component of gaze tracking, which transforms the eye coordinates to…
Neural architectures and hardware accelerators have been two driving forces for the progress in deep learning. Previous works typically attempt to optimize hardware given a fixed model architecture or model architecture given fixed…
Gait is a unique biometric feature that can be recognized at a distance; thus, it has broad applications in crime prevention, forensic identification, and social security. To portray a gait, existing gait recognition methods utilize either…
Existing visual object tracking usually learns a bounding-box based template to match the targets across frames, which cannot accurately learn a pixel-wise representation, thereby being limited in handling severe appearance variations. To…
Like many computer vision problems, human pose estimation is a challenging problem in that recognizing a body part requires not only information from local area but also from areas with large spatial distance. In order to spatially pass…
In today's landscape, Mixture of Experts (MoE) is a crucial architecture that has been used by many of the most advanced models. One of the major challenges of MoE models is that they usually require much more memory than their dense…
Indoor localization systems commonly rely on fingerprinting, which requires extensive survey efforts to obtain location-tagged signal data, limiting their real-world deployability. Recent approaches that attempt to reduce this overhead…
Memory prefetching has long boosted CPU caches and is increasingly vital for far-memory systems, where large portions of memory are offloaded to cheaper, remote tiers. While effective prefetching requires accurate prediction of future…
Temporal prefetching, where correlated pairs of addresses are logged and replayed on repeat accesses, has recently become viable in commercial designs. Arm's latest processors include Correlating Miss Chaining prefetchers, which store such…
Long-context modeling is a pivotal capability for Large Language Models, yet the quadratic complexity of attention remains a critical bottleneck, particularly during the compute-intensive prefilling phase. While various sparse attention…
Gait-based person re-identification (Re-ID) is valuable for safety-critical applications, and using only 3D skeleton data to extract discriminative gait features for person Re-ID is an emerging open topic. Existing methods either adopt…
Predicting where a person is looking is a complex task, requiring to understand not only the person's gaze and scene content, but also the 3D scene structure and the person's situation (are they manipulating? interacting or observing…
Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…
This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation. Unlike most existing approaches, we establish correspondences directly between frames without…
Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks. For example, one popular method, prefix-tuning, prepends trainable tokens to sequences while freezing the…
We discuss an attentional model for simultaneous object tracking and recognition that is driven by gaze data. Motivated by theories of perception, the model consists of two interacting pathways: identity and control, intended to mirror the…
This paper describes a new benchmark tool, Spatter, for assessing memory system architectures in the context of a specific category of indexed accesses known as gather and scatter. These types of operations are increasingly used to express…
Heterogeneity has grown in popularity both at the core and server level as a way to improve both performance and energy efficiency. However, despite these benefits, scheduling applications in heterogeneous machines remains challenging.…