Computer Vision – ACCV 2022 Workshops
16th Asian Conference on Computer Vision, Macao, China, December 4–8, 2022, Revised Selected Papers
Article
Video sequences exhibit significant nuisance variations (undesired effects) of speed of actions, temporal locations, and subjects’ poses, leading to temporal-viewpoint misalignment when comparing two sets of f...
Article
New roads are being constructed all the time. However, the capabilities of previous deep forecasting models to generalize to new roads not seen in the training data (unseen roads) are rarely explored. In this ...
Article
Contemporary deep learning multi-scale deblurring models suffer from many issues: (I) They perform poorly on non-uniformly blurred images/videos; (II) Simply increasing the model depth with finer-scale levels ...
Chapter and Conference Paper
We propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE). To factor out misalignment between query and support sequences of 3D ...
Chapter and Conference Paper
Current few-shot learning models capture visual object relations in the so-called meta-learning setting under a fixed-resolution input. However, such models have a limited generalization ability under the scal...
Book and Conference Proceedings
16th Asian Conference on Computer Vision, Macao, China, December 4–8, 2022, Revised Selected Papers
Chapter and Conference Paper
In this paper, we tackle the challenging problem of Few-shot Object Detection. Existing FSOD pipelines (i) use average-pooled representations that result in information loss; and/or (ii) discard position infor...
Chapter and Conference Paper
Dynamic Time War** (DTW) is used for matching pairs of sequences and celebrated in applications such as forecasting the evolution of time series, clustering time series or even matching sequence pairs in few...
Chapter and Conference Paper
In this paper, we tackle a challenging problem of Few-shot Object Detection rather than recognition. We propose Power Normalizing Second-order Detector consisting of the Encoding Network (EN), the Multi-scale ...
Chapter and Conference Paper
Sentence compression is a Natural Language Processing (NLP) task aimed at shortening original sentences and preserving their key information. Its applications can benefit many fields e.g., one can build tools for...
Chapter and Conference Paper
Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for spatio-temporal video blocks to ca...
Chapter and Conference Paper
Point-of-Interest (POI) recommendation is one of the most important location-based services hel** people discover interesting venues or services. However, the extreme user-POI matrix sparsity and the varying...
Chapter and Conference Paper
Inspired by optimization techniques, we propose a novel meta-learning algorithm with gradient modulation to encourage fast-adaptation of neural networks in the absence of abundant data. Our method, termed ModG...
Article
Given an artistic portrait, recovering the latent photorealistic face that preserves the subject’s identity is challenging because the facial details are often distorted or fully lost in artistic portraits. We...
Chapter and Conference Paper
In the problem of generalized zero-shot learning, the datapoints from unknown classes are not available during training. The main challenge for generalized zero-shot learning is the unbalanced data distributio...
Chapter and Conference Paper
We study an open problem of artwork identification and propose a new dataset dubbed Open Museum Identification Challenge (Open MIC). It contains photos of exhibits captured in 10 distinct exhibition spaces of ...
Chapter and Conference Paper
Aggregated second-order features extracted from deep convolutional networks have been shown to be effective for texture generation, fine-grained recognition, material classification, and scene understanding. I...
Chapter and Conference Paper
In this paper, we explore tensor representations that can compactly capture higher-order relationships between skeleton joints for 3D action recognition. We first define RBF kernels on 3D joint sequences, whic...