Related papers: A3D: Adaptive 3D Networks for Video Action Recogni…
The field of neural image compression has witnessed exciting progress as recently proposed architectures already surpass the established transform coding based approaches. While, so far, research has mainly focused on architecture and model…
Recently, 3D convolutional networks yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is very high. In this paper, we propose a fast but effective way…
Convolutional neural networks have enabled accurate image super-resolution in real-time. However, recent attempts to benefit from temporal correlations in video super-resolution have been limited to naive or inefficient architectures. In…
Traditionally, creating photo-realistic 3D head avatars requires a studio-level multi-view capture setup and expensive optimization during test-time, limiting the use of digital human doubles to the VFX industry or offline renderings. To…
This paper proposes a 3D shape descriptor network, which is a deep convolutional energy-based model, for modeling volumetric shape patterns. The maximum likelihood training of the model follows an "analysis by synthesis" scheme and can be…
We propose a data-driven scene flow estimation algorithm exploiting the observation that many 3D scenes can be explained by a collection of agents moving as rigid bodies. At the core of our method lies a deep architecture able to reason at…
Real-world network systems are inherently dynamic, with network topologies undergoing continuous changes over time. Previous works often focus on static networks or rely on complete prior knowledge of evolving topologies, whereas real-world…
Training Artificial Intelligence (AI) models on 3D images presents unique challenges compared to the 2D case: Firstly, the demand for computational resources is significantly higher, and secondly, the availability of large datasets for…
In this paper, we explore the spatial redundancy in video recognition with the aim to improve the computational efficiency. It is observed that the most informative region in each frame of a video is usually a small image patch, which…
Dense 3D reconstruction and ego-motion estimation are key challenges in autonomous driving and robotics. Compared to the complex, multi-modal systems deployed today, multi-camera systems provide a simpler, low-cost alternative. However,…
We present a method enabling the scaling of NeRFs to learn a large number of semantically-similar scenes. We combine two techniques to improve the required training time and memory cost per scene. First, we learn a 3D-aware latent space in…
Accurate estimation of production times is critical for effective manufacturing scheduling, yet traditional methods relying on expert analysis or historical data often fall short in dynamic or customized production environments. This paper…
Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…
Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is subject to human labeling bias. Similarly, there are multiple…
Reducing redundancy is crucial for improving the efficiency of video recognition models. An effective approach is to select informative content from the holistic video, yielding a popular family of dynamic video recognition methods.…
Predictable adaptation of network depths can be an effective way to control inference latency and meet the resource condition of various devices. However, previous adaptive depth networks do not provide general principles and a formal…
In recent years, video action recognition, as a fundamental task in the field of video understanding, has been deeply explored by numerous researchers.Most traditional video action recognition methods typically involve converting videos…
Similar to the notion of h-adaptivity, where the discretization resolution is adaptively changed, I propose the notion of model adaptivity, where the underlying model (the governing equations) is adaptively changed in space and time.…
Spatial intelligence is foundational to AI systems that interact with the physical world, particularly in 3D scene generation and spatial comprehension. Current methodologies for 3D scene generation often rely heavily on predefined…
3D structure modeling is essential across scales, enabling applications from fluid simulation and 3D reconstruction to protein folding and molecular docking. Yet, despite shared 3D spatial patterns, current approaches remain fragmented,…