Prior work on Sign Language Translation has shown that having a mid-level sign gloss representation (effectively recognizing the individual signs) improves the translation performance drastically. In fact, the current state-of-the-art in translation requires gloss level tokenization in order to work. We introduce a novel transformer based architecture that jointly learns Continuous Sign Language Recognition and Translation while being trainable in an end-to-end manner. This is achieved by using a Connectionist Temporal Classification (CTC) loss to bind the recognition and translation problems into a single unified architecture. This joint approach does not require any ground-truth timing information, simultaneously solving two co-dependant sequence-to-sequence learning problems and leads to significant performance gains.
We evaluate the recognition and translation performances of our approaches on the challenging RWTH-PHOENIX-Weather-2014T (PHOENIX14T) dataset. We report state-of-the-art sign language recognition and translation results achieved by our Sign Language Transformers. Our translation networks outperform both sign video to spoken language and gloss to spoken language translation models, in some cases more than doubling the performance (9.58 vs. 21.80 BLEU-4 Score). We also share new baseline translation results using transformer networks for several other text-to-text sign language translation tasks.
Sign Language Translation (SLT) first uses a Sign Language Recognition (SLR) system to extract sign language glosses from videos. Then, a translation system generates spoken language translations from the sign language glosses. This paper focuses on the translation system and introduces the STMC-Transformer which improves on the current state-of-the-art by over 5 and 7 BLEU respectively on gloss-to-text and video-to-text translation of the PHOENIX-Weather 2014T dataset. On the ASLG-PC12 corpus, we report an increase of over 16 BLEU. We also demonstrate the problem in current methods that rely …
Fingerprint recognition has drawn a lot of attention during last decades. Different features and algorithms have been used for fingerprint recognition in the past. In this paper, a powerful image representation called scattering transform/network, is used for recognition. Scattering network is a convolutional network where its architecture and filters are predefined wavelet transforms. The first layer of scattering representation is similar to sift descriptors and the higher layers capture higher frequency content of the signal. After extraction of scattering features, their dimensionality is …
LiDAR based place recognition is popular for loop closure detection and re-localization. In recent years, deep learning brings improvements to place recognition by learnable feature extraction. However, these methods degenerate when the robot re-visits previous places with large perspective difference. To address the challenge, we propose DeepRING to learn the roto-translation invariant representation from LiDAR scan, so that robot visits the same place with different perspective can have similar representations. There are two keys in DeepRING: the feature is extracted from sinogram, and the f…
Cross-modal transfer is helpful to enhance modality-specific discriminative power for scene recognition. To this end, this paper presents a unified framework to integrate the tasks of cross-modal translation and modality-specific recognition, termed as Translate-to-Recognize Network (TRecgNet). Specifically, both translation and recognition tasks share the same encoder network, which allows to explicitly regularize the training of recognition task with the help of translation, and thus improve its final generalization ability. For translation task, we place a decoder module on top of the encod…
Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial examples, raising concerns about the robustness of such systems. Adversarial examples that are not restricted to small perturbations could be more serious since conventional certified defenses might be ineffective against them. To shed light on the vulnerability to such adversarial examples, we propose a flexible and efficient method for generating unrestricted…
Microsoft Research（微软研究院）；Microsoft（微软公司）；Rochester Institute of Technology（罗切斯特理工学院）；Gallaudet University（加劳德特大学）；LIMSI（LIMSI实验室）；CNRS（法国国家科学研究中心）；Paris-Saclay University（巴黎萨克雷大学）；Boston University（波士顿大学）；University of Maryland（马里兰大学）；Leiden University（莱顿大学）
Developing successful sign language recognition, generation, and translation systems requires expertise in a wide range of fields, including computer vision, computer graphics, natural language processing, human-computer interaction, linguistics, and Deaf culture. Despite the need for deep interdisciplinary knowledge, existing research occurs in separate disciplinary silos, and tackles separate portions of the sign language processing pipeline. This leads to three key questions: 1) What does an interdisciplinary view of the current landscape reveal? 2) What are the biggest challenges facing th…
Microsoft Research Asia（微软亚洲研究院）；The Hong Kong University of Science and Technology（香港科技大学）
Sign languages are visual languages using manual articulations and non-manual elements to convey information. For sign language recognition and translation, the majority of existing approaches directly encode RGB videos into hidden representations. RGB videos, however, are raw signals with substantial visual redundancy, leading the encoder to overlook the key information for sign language understanding. To mitigate this problem and better incorporate domain knowledge, such as handshape and body movement, we introduce a dual visual encoder containing two separate streams to model both the raw v…
In the past decades the set of human tasks that are solved by machines was extended dramatically. From simple image classification problems researchers now move towards solving more sophisticated and vital problems, like, autonomous driving and language translation. The case of language translation includes a challenging area of sign language translation that incorporates both image and language processing. We make a step in that direction by proposing a lightweight network for ASL gesture recognition with a performance sufficient for practical applications. The proposed solution demonstrates …
Multi-media communications facilitate global interaction among people. However, despite researchers exploring cross-lingual translation techniques such as machine translation and audio speech translation to overcome language barriers, there is still a shortage of cross-lingual studies on visual speech. This lack of research is mainly due to the absence of datasets containing visual speech and translated text pairs. In this paper, we present \textbf{AVMuST-TED}, the first dataset for \textbf{A}udio-\textbf{V}isual \textbf{Mu}ltilingual \textbf{S}peech \textbf{T}ranslation, derived from \textbf{…
This paper presents an image classification based approach for skeleton-based video action recognition problem. Firstly, A dataset independent translation-scale invariant image mapping method is proposed, which transformes the skeleton videos to colour images, named skeleton-images. Secondly, A multi-scale deep convolutional neural network (CNN) architecture is proposed which could be built and fine-tuned on the powerful pre-trained CNNs, e.g., AlexNet, VGGNet, ResNet etal.. Even though the skeleton-images are very different from natural images, the fine-tune strategy still works well. At last…
University of Central Florida（中佛罗里达大学）；Hacettepe University（哈塞特佩大学）
Facial expression recognition is a challenging task due to two major problems: the presence of inter-subject variations in facial expression recognition dataset and impure expressions posed by human subjects. In this paper we present a novel Human-to-Animation conditional Generative Adversarial Network (HA-GAN) to overcome these two problems by using many (human faces) to one (animated face) mapping. Specifically, for any given input human expression image, our HA-GAN transfers the expression information from the input image to a fixed animated identity. Stylized animated characters from the F…
Chonbuk National University（韩国全北国立大学）；Mokpo National University（韩国木浦国立大学）
Acquisition of data in task-specific applications of machine learning like plant disease recognition is a costly endeavor owing to the requirements of professional human diligence and time constraints. In this paper, we present a simple pipeline that uses GANs in an unsupervised image translation environment to improve learning with respect to the data distribution in a plant disease dataset, reducing the partiality introduced by acute class imbalance and hence shifting the classification decision boundary towards better performance. The empirical analysis of our method is demonstrated on a li…
State-of-the-art deep neural network models have reached near perfect face recognition accuracy rates on controlled high-resolution face images. However, their performance is drastically degraded when they are tested with very low-resolution face images. This is particularly critical in surveillance systems, where a low-resolution probe image is to be matched with high-resolution gallery images. super-resolution techniques aim at producing high-resolution face images from low-resolution counterparts. While they are capable of reconstructing images that are visually appealing, the identity-rela…
The performance of Human Activity Recognition (HAR) models, particularly deep neural networks, is highly contingent upon the availability of the massive amount of annotated training data which should be sufficiently labeled. Though, data acquisition and manual annotation in the HAR domain are prohibitively expensive due to skilled human resource requirements in both steps. Hence, domain adaptation techniques have been proposed to adapt the knowledge from the existing source of data. More recently, adversarial transfer learning methods have shown very promising results in image classification, …
Multi-Stream Keypoint Attention Network for Sign Language Recognition and Translation
School of Information Science and Engineering, Shenyang University of Technology（沈阳工业大学信息科学与工程学院）；School of Software, Shenyang University of Technology（沈阳工业大学软件学院）
Hochschule Bonn-Rhein-Sieg（波恩-莱茵-锡格应用技术大学）；German Research Center for Artificial Intelligence（德国人工智能研究中心）
Traffic sign recognition is an important component of many advanced driving assistance systems, and it is required for full autonomous driving. Computational performance is usually the bottleneck in using large scale neural networks for this purpose. SqueezeNet is a good candidate for efficient image classification of traffic signs, but in our experiments it does not reach high accuracy, and we believe this is due to lack of data, requiring data augmentation. Generative adversarial networks can learn the high dimensional distribution of empirical data, allowing the generation of new data point…
Beijing University of Posts and Telecommunications（北京邮电大学）；Kuaishou Technology（快手科技）
Unpaired image-to-image translation is to translate an image from a source domain to a target domain without paired training data. By utilizing CNN in extracting local semantics, various techniques have been developed to improve the translation performance. However, CNN-based generators lack the ability to capture long-range dependency to well exploit global semantics. Recently, Vision Transformers have been widely investigated for recognition tasks. Though appealing, it is inappropriate to simply transfer a recognition-based vision transformer to image-to-image translation due to the generati…
University of Science and Technology of China（中国科学技术大学）；University of Technology Sydney（悉尼科技大学）
Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in meaningful objects in input. Sometimes, such networks are trained using data augmentation to encode this invariance into the parameters, which restricts the capacity of the model to learn the content of these objects. A more efficient use of the parameter budget is to encode rotation or translation invariance into the model architecture, which relieves the mod…
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）
Point cloud recognition is an essential task in industrial robotics and autonomous driving. Recently, several point cloud processing models have achieved state-of-the-art performances. However, these methods lack rotation robustness, and their performances degrade severely under random rotations, failing to extend to real-world scenarios with varying orientations. To this end, we propose a method named Self Contour-based Transformation (SCT), which can be flexibly integrated into various existing point cloud recognition models against arbitrary rotations. SCT provides efficient rotation and tr…
In-Context Translation: Towards Unifying Image Recognition, Processing, and Generation
Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University（上海交通大学图像通信与网络工程研究所）；School of Information Systems, Singapore Management University（新加坡管理大学信息系统学院）；MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院（教育部人工智能重点实验室））；School of Electronics and Computer Science, University of Southampton（南安普顿大学电子与计算机科学学院）
Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University（复旦大学计算机科学技术学院上海市智能信息处理重点实验室）；Shanghai Collaborative Innovation Center on Intelligent Visual Computing（上海智能视觉计算协同创新中心）
Although deep-learning based video recognition models have achieved remarkable success, they are vulnerable to adversarial examples that are generated by adding human-imperceptible perturbations on clean video samples. As indicated in recent studies, adversarial examples are transferable, which makes it feasible for black-box attacks in real-world applications. Nevertheless, most existing adversarial attack methods have poor transferability when attacking other video models and transfer-based attacks on video models are still unexplored. To this end, we propose to boost the transferability of …
Beihang University（北京航空航天大学）；Polytechnic University of Milan（米兰理工大学）
Motion trajectory recognition is important for characterizing the moving property of an object. The speed and accuracy of trajectory recognition rely on a compact and discriminative feature representation, and the situations of varying rotation, scaling and translation has to be specially considered. In this paper we propose a novel feature extraction method for trajectories. Firstly a trajectory is represented by a proposed point context, which is a rotation-scale-translation (RST) invariant shape descriptor with a flexible tradeoff between computational complexity and discrimination, yet we …
University of South Toulon - Var（南土伦-瓦尔大学）；University of Paris-Dauphine（巴黎第九大学）
In this paper we propose a supervised object recognition method using new global features and inspired by the model of the human primary visual cortex V1 as the semidiscrete roto-translation group $SE(2,N) = \mathbb Z_N\rtimes \mathbb R^2$. The proposed technique is based on generalized Fourier descriptors on the latter group, which are invariant to natural geometric transformations (rotations, translations). These descriptors are then used to feed an SVM classifier. We have tested our method against the COIL-100 image database and the ORL face database, and compared it with other techniques b…
Zhejiang University（浙江大学）；Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海高等研究院）；Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）；Hangzhou Honghua Digital Technology Co., Ltd.（杭州宏华数码科技股份有限公司）；Ningbo Research Institute, Zhejiang University（浙江大学宁波研究院）
Deep learning has recently achieved remarkable performance in image classification tasks, which depends heavily on massive annotation. However, the classification mechanism of existing deep learning models seems to contrast to humans' recognition mechanism. With only a glance at an image of the object even unknown type, humans can quickly and precisely find other same category objects from massive images, which benefits from daily recognition of various objects. In this paper, we attempt to build a generalizable framework that emulates the humans' recognition mechanism in the image classificat…
Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method
LIVIA, Dept. of Systems Engineering, ETS Montreal, Canada（蒙特利尔工程学院系统工程系LIVIA）；LIVIA, Dept. of Software and IT Engineering, ETS Montreal, Canada（蒙特利尔工程学院软件与IT工程系LIVIA）；Dept. of Health, Kinesiology, & Applied Physiology, Concordia University, Montreal, Canada（蒙特利尔大学健康、运动科学与应用生理学系）；Montreal Behavioural Medicine Centre, CIUSSS Nord-de-l’Ile-de-Montréal, Canada（蒙特利尔行为医学中心，北岛-蒙特利尔CIUSSS）；Dept. of Electrical and Computer Engineering, Queen’s University, Kingston, Canada（皇后大学电气与计算机工程系）
