arXiv subjects

Jingwei Ji

Publications and source records attributed to Jingwei Ji.

21 records · Page 2Linked to original sources

arXiv2019

Few-Shot Video Classification via Temporal Alignment

There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a novel few-shot learning framework that can learn to classify a previous unseen video. While most previous works neglect long-term temporal ordering information, our proposed model explicitly leverages the temporal ordering information in video data through temporal alignment. This leads to strong data-efficiency for few-shot learning. In concrete, TAM calculates the distance value of query video with respect to novel class proxies by averaging the per frame distances along its alignment path. We introduce continuous relaxation to TAM so the model can be learned in an end-to-end fashion to directly optimize the few-shot learning objective. We evaluate TAM on two challenging real-world datasets, Kinetics and Something-Something-V2, and show that our model leads to significant improvement of few-shot video classification over a wide range of competitive baselines.

cs.CV↗

arXiv2017

Tests of Cold Atom Clock in Orbit

Since the atomic clock was invented, its performance has been improved for one digit every decade until 90s of last century when the traditional atomic clock almost reached its limit. With laser cooled atoms, the performance can be further improved, and nowadays the cold atom based clocks are widely used as primary frequency standards. Such a kind of cold atom clocks has great applications in space. This paper presents the design and tests of a cold atom clock (CAC) operating in space. In microgravity, the atoms are cooled, trapped, launched and finally detected after being interrogated by microwave field with Ramsey method. The results of laser cooling of atoms in microgravity in orbit are presented and compared with that on ground for the first time. That the full width at half maximum (FWHM) of obtained central Ramsey fringes varies linearly with launching velocity of cold atoms shows the effects of microgravity. With appropriate parameters, a closed-loop locking of the CAC is realized in orbit and the estimated short term frequency stability of $3.0\times 10 ^{-13}/\sqrt{τ}$ has been reached.

physics.atom-ph↗

arXiv2017

DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image

3D reconstruction from a single image is a key problem in multiple applications ranging from robotic manipulation to augmented reality. Prior methods have tackled this problem through generative models which predict 3D reconstructions as voxels or point clouds. However, these methods can be computationally expensive and miss fine details. We introduce a new differentiable layer for 3D data deformation and use it in DeformNet to learn a model for 3D reconstruction-through-deformation. DeformNet takes an image input, searches the nearest shape template from a database, and deforms the template to match the query image. We evaluate our approach on the ShapeNet dataset and show that - (a) the Free-Form Deformation layer is a powerful new building block for Deep Learning models that manipulate 3D data (b) DeformNet uses this FFD layer combined with shape retrieval for smooth and detail-preserving 3D reconstruction of qualitatively plausible point clouds with respect to a single query image (c) compared to other state-of-the-art 3D reconstruction methods, DeformNet quantitatively matches or outperforms their benchmarks by significant margins. For more information, visit: https://deformnet-site.github.io/DeformNet-website/ .

cs.CV↗