相关论文: Modeling State Shifting via Local-Global Distillat…

Human motion prediction is important for many virtual and augmented reality (VR/AR) applications such as collision avoidance and realistic avatar generation. Existing methods have synthesised body motion only from observed past motion,…

In this paper, we evaluate a synthetic framework to be used in the field of gaze estimation employing deep learning techniques. The lack of sufficient annotated data could be overcome by the utilization of a synthetic evaluation framework…

Learning-based methods commonly treat state estimation in robotics as a sequence modeling problem. While this paradigm can be effective at maximizing end-to-end performance, models are often difficult to interpret and expensive to train,…

Anticipating future actions in a video is useful for many autonomous and assistive technologies. Most prior action anticipation work treat this as a vision modality problem, where the models learn the task information primarily from the…

Eye feature extraction from event-based data streams can be performed efficiently and with low energy consumption, offering great utility to real-world eye tracking pipelines. However, few eye feature extractors are designed to handle…

Over the past few years, there has been an increasing interest to interpret gaze direction in an unconstrained environment with limited supervision. Owing to data curation and annotation issues, replicating gaze estimation method to other…

Knowledge distillation is a widely used paradigm for inheriting information from a complicated teacher network to a compact student network and maintaining the strong performance. Different from image classification, object detectors are…

Human pose estimation has been widely applied in the human-centric understanding and generation, but most existing state-of-the-art human pose estimation methods require heavy computational resources for accurate predictions. In order to…

This paper addresses the problem of model compression via knowledge distillation. To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from…

We present a semantics modulated, multi scale Transformer for 3D gaze estimation. Our model conditions CLIP global features with learnable prototype banks (illumination, head pose, background, direction), fuses these prototype-enriched…

Gaze estimation methods often experience significant performance degradation when evaluated across different domains, due to the domain gap between the testing and training data. Existing methods try to address this issue using various…

Along with the recent development of deep neural networks, appearance-based gaze estimation has succeeded considerably when training and testing within the same domain. Compared to the within-domain task, the variance of different domains…

We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully…

DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge…

In recent years, the accuracy of gaze estimation techniques has gradually improved, but existing methods often rely on large datasets or large models to improve performance, which leads to high demands on computational resources. In terms…

Appearance-based gaze estimation provides relatively unconstrained gaze tracking. However, subject-independent models achieve limited accuracy partly due to individual variations. To improve estimation, we propose a novel gaze decomposition…

Event cameras are gaining popularity due to their unique properties, such as their low latency and high dynamic range. One task where these benefits can be crucial is real-time object detection. However, RGB detectors still outperform…

Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to…

In many practical scenarios, the dynamical system is not available and standard data assimilation methods are not applicable. Our objective is to construct a data-driven model for state estimation without the underlying dynamics. Instead of…

Model distillation enables the transfer of knowledge from large-scale models to compact student models, facilitating deployment in resource-constrained environments. However, conventional distillation approaches often suffer from…