Sorry, you need to enable JavaScript to visit this website.

As an essential task for natural language understanding, slot filling aims to identify the contiguous spans of specific slots in an utterance. In real-world applications, the labeling costs of utterances may be expensive, and transfer learning techniques have been developed to ease this problem. However, cross-domain slot filling could significantly suffer from negative transfer due to non-targeted or zero-shot slots.

Recent years have witnessed a growing interest in online RGB-D 3D reconstruction. On the premise of ensuring the reconstruction accuracy with noisy depth scans, making the system scalable to various environments is still challenging. In this paper, we devote our efforts to try to fill in this research gap by proposing a scalable and robust RGB-D 3D reconstruction framework, namely ChunkFusion. In ChunkFusion, sparse voxel management is exploited to improve the scalability of online reconstruction.

Modern codecs offer numerous settings that can nonuniformly alter the encoding process. Some researchers have proposed video encoding multiobjective optimization, but none of these proposals addresses optimization of the entire encoder's option space when it is large. In this paper, we present a method for multiobjective encoding optimization of a given encoder in terms of relative video bitrate and encoding speed. The process takes place over one or more videos against a set of reference presets. It actively exploits similarities in the encoding process for similar videos.

Analyzing large-scale data from simulations of turbulent flows is memory intensive, requiring significant resources. This major challenge highlights the need for data compression techniques. In this study, we apply a physics-informed Deep Learning technique based on vector quantization to generate a discrete, low-dimensional representation of data from simulations of three-dimensional turbulent flows.

Several computer vision applications such as person search or online fashion rely on human description. The use of instance-level human parsing (HP) is therefore relevant since it localizes semantic attributes and body parts within a person. But how to characterize these attributes? To our knowledge, only some single-HP datasets describe attributes with some color, size and/or pattern characteristics. There is a lack of dataset for multi-HP in the wild with such characteristics.

We address 3D human pose and shape estimations from multi-view images. We use the SMPL body model, and regress the model parameters that best fit the shape and pose. To solve for the parameters, we first compute 3D joint positions from 2D joint estimations on images by using a linear algebraic triangulation. Then, we fit the 3D parametric body model to the 3D joints while imposing a bone orientation constraint between the 3D model and the corresponding body parts detected in the images.

Human pose estimation is a long-standing and challenging problem in computer vision. Many recent advancements in the field have relied on complex structure refinement and specific human joint graphical relations. However, progress has been saturated in terms of accuracy. Each time, new state-of-the-art approaches only improve accuracy by less than 0.3% in the MPII test set despite using complicated model structures.