This paper is a brief report to our submission to the VIPriors Action Recognition Challenge. Action recognition has attracted many researchers attention for its full application, but it is still challenging. In this paper, we study previous methods and propose our method. In our method, we are primarily making improvements on the SlowFast Network and fusing with TSM to make further breakthroughs. Also, we use a fast but effective way to extract motion features from videos by using residual frames as input. Better motion features can be extracted using residual frames with SlowFast, and the residual-frame-input path is an excellent supplement for existing RGB-frame-input models. And better performance obtained by combining 3D convolution(SlowFast) with 2D convolution(TSM). The above experiments were all trained from scratch on UCF101.
Center for Research in Computer Vision (CRCV), University of Central Florida（中佛罗里达大学计算机视觉研究中心）；Indian Institute of Technology, Kanpur（坎普尔印度理工学院）
This technical report presents our approach "Knights" to solve the action recognition task on a small subset of Kinetics-400 i.e. Kinetics400ViPriors without using any extra-data. Our approach has 3 main components: state-of-the-art Temporal Contrastive self-supervised pretraining, video transformer models, and optical flow modality. Along with the use of standard test-time augmentation, our proposed solution achieves 73% on Kinetics400ViPriors test set, which is the best among all of the other entries Visual Inductive Priors for Data-Efficient Computer Vision's Action Recognition Challenge, I…
University of Oulu（奥卢大学）；Delft University of Technology（代尔夫特理工大学）
To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle overfitting problems. However, it limits the research within organizations that have strong computational abilities. In this work, we try to propose a data-efficient framework that can train the model from scratch on small datasets while achieving promising results. Specifically, by introducing a 3D central difference convolution operation, we proposed a novel C3D …
Yonsei University（延世大学）；Cognex Deep Learning Lab（康耐视深度学习实验室）
Deep-Learning-based video recognition has shown promising improvements along with the development of large-scale datasets and spatiotemporal network architectures. In image recognition, learning spatially invariant features is a key factor in improving recognition performance and robustness. Data augmentation based on visual inductive priors, such as cropping, flipping, rotating, or photometric jittering, is a representative approach to achieve these features. Recent state-of-the-art recognition solutions have relied on modern data augmentation strategies that exploit a mixture of augmentation…
Image classification has always been a hot and challenging task. This paper is a brief report to our submission to the VIPriors Image Classification Challenge. In this challenge, the difficulty is how to train the model from scratch without any pretrained weight. In our method, several strong backbones and multiple loss functions are used to learn more representative features. To improve the models' generalization and robustness, efficient image augmentation strategies are utilized, like autoaugment and cutmix. Finally, ensemble learning is used to increase the performance of the models. The f…
Person re-identification has always been a hot and challenging task. This paper introduces our solution for the re-identification track in VIPriors Challenge 2021. In this challenge, the difficulty is how to train the model from scratch without any pretrained weight. In our method, we show use state-of-the-art data processing strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. (1) Both image augmentation strategy and novel pre-processing method for occluded images can help the model learn mo…
This paper is a brief report to our submission to the VIPriors Object Detection Challenge. Object Detection has attracted many researchers' attention for its full application, but it is still a challenging task. In this paper, we study analysis the characteristics of the data, and an effective data enhancement method is proposed. We carefully choose the model which is more suitable for training from scratch. We benefit a lot from using softnms and model fusion skillfully.
In this report, we descibe our approach to the ECCV 2020 VIPriors Object Detection Challenge which took place from March to July in 2020. We show that by using state-of-the-art data augmentation strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. Notably, our overall detection system achieves 36.6$\%$ AP on the COCO 2017 validation set using only 10K training images without any pre-training or transfer learning weights ranking us 2nd place in the challenge.
DIVUS corp.（DIVUS公司）；DeltaX corp.（DeltaX公司）；DP World（DP世界公司）；Kumoh National Institute of Technology（庆熙大学（注：此处原机构名称为Kumoh National Institute of Technology，常见中文名应为“公州大学”，但根据要求保留原文并翻译，此处可能存在翻译准确性问题，需注意））
Copy-Paste has proven to be a very effective data augmentation for instance segmentation which can improve the generalization of the model. We used a task-specific Copy-Paste data augmentation method to achieve good performance on the instance segmentation track of the 2nd VIPriors workshop challenge. We also applied additional data augmentation techniques including RandAugment and GridMask. Our segmentation model is the HTC detector on the CBSwin-B with CBFPN with some tweaks. This model was trained at the multi-scale mode by a random sampler on the 6x schedule and tested at the single-scale …
Huaqiao University（华侨大学）；Wuhan University of Technology（武汉理工大学）
In this report, we introduce the technical details of our submission to the VIPriors object detection challenge. Our solution is based on mmdetction of a strong baseline open-source detection toolbox. Firstly, we introduce an effective data augmentation method to address the lack of data problem, which contains bbox-jitter, grid-mask, and mix-up. Secondly, we present a robust region of interest (ROI) extraction method to learn more significant ROI features via embedding global context features. Thirdly, we propose a multi-model integration strategy to refinement the prediction box, which weigh…
Institute for Infocomm Research, Agency for Science, Technology and Research（新加坡科技研究局资讯通信研究院）；National University of Singapore（新加坡国立大学）
In this report, we present the technical details of our submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition 2022. This task aims to adapt an action recognition model trained on a labeled source domain to an unlabeled target domain. To achieve this goal, we propose an action-aware domain adaptation framework that leverages the prior knowledge induced from the action recognition task during the adaptation. Specifically, we disentangle the source features into action-relevant features and action-irrelevant features using the learned action cla…
Institute of Industrial Science, the University of Tokyo（东京大学生产技术研究所）
In this report, we describe the technical details of our submission to the 2021 EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition. Leveraging multiple modalities has been proved to benefit the Unsupervised Domain Adaptation (UDA) task. In this work, we present Multi-Modal Mutual Enhancement Module (M3EM), a deep module for jointly considering information from multiple modalities to find the most transferable representations across domains. We achieve this by implementing two sub-modules for enhancing each modality using the context of other modalities. The first…
In this report, we present the technical details of our submission to the 2022 EPIC-Kitchens Unsupervised Domain Adaptation (UDA) Challenge. Existing UDA methods align the global features extracted from the whole video clips across the source and target domains but suffer from the spatial redundancy of feature matching in video recognition. Motivated by the observation that in most cases a small image region in each video frame can be informative enough for the action recognition task, we propose to exploit informative image regions to perform efficient domain alignment. Specifically, we first…
Ulsan National Institute of Science and Technology (UNIST)（蔚山科学技术院（UNIST））
This report describes the 2nd place solution to the ECCV 2022 Human Body, Hands, and Activities (HBHA) from Egocentric and Multi-view Cameras Challenge: Action Recognition. This challenge aims to recognize hand-object interaction in an egocentric view. We propose a framework that estimates keypoints of two hands and an object with a Transformer-based keypoint estimator and recognizes actions based on the estimated keypoints. We achieved a top-1 accuracy of 87.19% on the testset.
Knexus Research Corporation（克奈苏斯研究公司）；Naval Research Laboratory（美国海军研究实验室）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
Convolutional Architecture for Fast Feature Encoding (CAFFE) [11] is a software package for the training, classifying, and feature extraction of images. The UCF Sports Action dataset is a widely used machine learning dataset that has 200 videos taken in 720x480 resolution of 9 different sporting activities: diving, golf, swinging, kicking, lifting, horseback riding, running, skateboarding, swinging (various gymnastics), and walking. In this report we report on a caffe feature extraction pipeline of images taken from the videos of the UCF Sports Action dataset. A similar test was performed on o…
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；Computer Vision Center（计算机视觉中心）；Universitat de Barcelona（巴塞罗那大学）
In this report we describe the technical details of our submission to the EPIC-Kitchens 2019 action recognition challenge. To participate in the challenge we have developed a number of CNN-LSTA [3] and HF-TSN [2] variants, and submitted predictions from an ensemble compiled out of these two model families. Our submission, visible on the public leaderboard with team name FBK-HUPBA, achieved a top-1 action recognition accuracy of 35.54% on S1 setting, and 20.25% on S2 setting.
In this paper, we report on experiments with the use of local measures for depth motion for visual action recognition from MPEG encoded RGBD video sequences. We show that such measures can be combined with local space-time video descriptors for appearance to provide a computationally efficient method for recognition of actions. Fisher vectors are used for encoding and concatenating a depth descriptor with existing RGB local descriptors. We then employ a linear SVM for recognizing manipulation actions using such vectors. We evaluate the effectiveness of such measures by comparison to the state-…
Nankai University（南开大学）；Bytedance Inc.（字节跳动公司）；University of Science and Technology Beijing（北京科技大学）
Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition. This work shows that CMAE also trivially generalizes well on video action recognition without modifying the architecture and the loss criterion. By directly replacing the original pixel shift with the temporal shift, our CMAE for visual action recognition, CMAE-V for short, can generate stronger feature representations than its counterpart based on pure masked autoencoders. Notably, CMAE-V, with a hybrid architecture, can…
We benchmark contemporary action recognition models (TSN, TRN, and TSM) on the recently introduced EPIC-Kitchens dataset and release pretrained models on GitHub (https://github.com/epic-kitchens/action-models) for others to build upon. In contrast to popular action recognition datasets like Kinetics, Something-Something, UCF101, and HMDB51, EPIC-Kitchens is shot from an egocentric perspective and captures daily actions in-situ. In this report, we aim to understand how well these models can tackle the challenges present in this dataset, such as its long tail class distribution, unseen environme…
University of Science and Technology of China（中国科学技术大学）；JD AI Research（京东人工智能研究院）
This technical report introduces our 2nd place solution to Kinetics-TPS Track on Part-level Action Parsing in ICCV DeeperAction Workshop 2021. Our entry is mainly based on YOLOF for instance and part detection, HRNet for human pose estimation, and CSN for video-level action recognition and frame-level part state parsing. We describe technical details for the Kinetics-TPS dataset, together with some experimental results. In the competition, we achieved 61.37% mAP on the test set of Kinetics-TPS.
The Chinese University of HongKong（香港中文大学）；Shanghai AI Laboratory（上海人工智能实验室）
We present PYSKL: an open-source toolbox for skeleton-based action recognition based on PyTorch. The toolbox supports a wide variety of skeleton action recognition algorithms, including approaches based on GCN and CNN. In contrast to existing open-source skeleton action recognition projects that include only one or two algorithms, PYSKL implements six different algorithms under a unified framework with both the latest and original good practices to ease the comparison of efficacy and efficiency. We also provide an original GCN-based skeleton action recognition model named ST-GCN++, which achie…
Fondazione Bruno Kessler - FBK（布鲁诺·凯斯勒基金会（FBK））；Computer Vision Center（计算机视觉中心）；Universitat de Barcelona（巴塞罗那大学）
In this report we describe the technical details of our submission to the EPIC-Kitchens Action Recognition 2020 Challenge. To participate in the challenge we deployed spatio-temporal feature extraction and aggregation models we have developed recently: Gate-Shift Module (GSM) [1] and EgoACO, an extension of Long Short-Term Attention (LSTA) [2]. We design an ensemble of GSM and EgoACO model families with different backbones and pre-training to generate the prediction scores. Our submission, visible on the public leaderboard with team name FBK-HUPBA, achieved a top-1 action recognition accuracy …
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）
In this report, we present the technical details of our approach to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition. The EPIC-KITCHENS-100 dataset consists of daily kitchen activities focusing on the interaction between human hands and their surrounding objects. It is very challenging to accurately recognize these fine-grained activities, due to the presence of distracting objects and visually similar action classes, especially in the unlabelled target domain. Based on an existing method for video domain adaptation, i.e., TA3N, we propose to learn ha…
Infrared (IR) imaging has the potential to enable more robust action recognition systems compared to visible spectrum cameras due to lower sensitivity to lighting conditions and appearance variability. While the action recognition task on videos collected from visible spectrum imaging has received much attention, action recognition in IR videos is significantly less explored. Our objective is to exploit imaging data in this modality for the action recognition task. In this work, we propose a novel two-stream 3D convolutional neural network (CNN) architecture by introducing the discriminative c…
Sign Language Recognition (SLR) is an essential yet challenging task since sign language is performed with the fast and complex movement of hand gestures, body posture, and even facial expressions. %Skeleton Aware Multi-modal Sign Language Recognition In this work, we focused on investigating two questions: how fine-tuning on datasets from other sign languages helps improve sign recognition quality, and whether sign recognition is possible in real-time without using GPU. Three different languages datasets (American sign language WLASL, Turkish - AUTSL, Russian - RSL) have been used to validate…
Imperial College London（伦敦帝国理工学院）；InsightFace；Tsinghua University（清华大学）
During the COVID-19 coronavirus epidemic, almost everyone wears a facial mask, which poses a huge challenge to deep face recognition. In this workshop, we organize Masked Face Recognition (MFR) challenge and focus on bench-marking deep face recognition methods under the existence of facial masks. In the MFR challenge, there are two main tracks: the InsightFace track and the WebFace260M track. For the InsightFace track, we manually collect a large-scale masked face test set with 7K identities. In addition, we also collect a children test set including 14K identities and a multi-racial test set …
This report explores the latest advances in the field of digital document recognition. With the focus on printed document imagery, we discuss the major developments in optical character recognition (OCR) and document image enhancement/restoration in application to Latin and non-Latin scripts. In addition, we review and discuss the available technologies for hand-written document recognition. In this report, we also provide some company-accumulated benchmark results on available OCR engines.
This report concerns the use of techniques for sparse signal representation and sparse error correction for automatic face recognition. Much of the recent interest in these techniques comes from the paper "Robust Face Recognition via Sparse Representation" by Wright et al. (2009), which showed how, under certain technical conditions, one could cast the face recognition problem as one of seeking a sparse representation of a given input face image in terms of a "dictionary" of training images and images of individual pixels. In this report, we have attempted to clarify some frequently encountere…
Face recognition performance improves rapidly with the recent deep learning technique developing and underlying large training dataset accumulating. In this paper, we report our observations on how big data impacts the recognition performance. According to these observations, we build our Megvii Face Recognition System, which achieves 99.50% accuracy on the LFW benchmark, outperforming the previous state-of-the-art. Furthermore, we report the performance in a real-world security certification scenario. There still exists a clear gap between machine recognition and human performance. We summari…
Tsinghua University（清华大学）；XForwardAI；Imperial College London（伦敦帝国理工学院）；InsightFace
According to WHO statistics, there are more than 204,617,027 confirmed COVID-19 cases including 4,323,247 deaths worldwide till August 12, 2021. During the coronavirus epidemic, almost everyone wears a facial mask. Traditionally, face recognition approaches process mostly non-occluded faces, which include primary facial features such as the eyes, nose, and mouth. Removing the mask for authentication in airports or laboratories will increase the risk of virus infection, posing a huge challenge to current face recognition systems. Due to the sudden outbreak of the epidemic, there are yet no publ…
Ultra Light OCR Competition is a Chinese scene text recognition competition jointly organized by CSIG (China Society of Image and Graphics) and Baidu, Inc. In addition to focusing on common problems in Chinese scene text recognition, such as long text length and massive characters, we need to balance the trade-off of model scale and accuracy since the model size limitation in the competition is 10M. From experiments in aspects of data, model, training, etc, we proposed a general and effective method for Chinese scene text recognition, which got us second place among over 100 teams with accurac…
We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art ac…
Scene text recognition has attracted increasing interest in recent years due to its wide range of applications in multilingual translation, autonomous driving, etc. In this report, we describe our solution to the Out of Vocabulary Scene Text Understanding (OOV-ST) Challenge, which aims to extract out-of-vocabulary (OOV) words from natural scene images. Our oCLIP-based model achieves 28.59\% in h-mean which ranks 1st in end-to-end OOV word recognition track of OOV Challenge in ECCV2022 TiE Workshop.
University of Manchester（曼彻斯特大学）；Sudan University of Science and Technology（苏丹科技大学）；Manchester Metropolitan University（曼彻斯特城市大学）
Micro-expressions are brief spontaneous facial expressions that appear on a face when a person conceals an emotion, making them different to normal facial expressions in subtlety and duration. Currently, emotion classes within the CASME II dataset are based on Action Units and self-reports, creating conflicts during machine learning training. We will show that classifying expressions using Action Units, instead of predicted emotion, removes the potential bias of human reporting. The proposed classes are tested using LBP-TOP, HOOF and HOG 3D feature descriptors. The experiments are evaluated on…
AllRead MLT；Computer Vision Center, Universitat Autonoma de Barcelona（巴塞罗那自治大学计算机视觉中心）；AWS AI Labs（亚马逊云科技人工智能实验室）
This paper presents final results of the Out-Of-Vocabulary 2022 (OOV) challenge. The OOV contest introduces an important aspect that is not commonly studied by Optical Character Recognition (OCR) models, namely, the recognition of unseen scene text instances at training time. The competition compiles a collection of public scene text datasets comprising of 326,385 images with 4,864,405 scene text instances, thus covering a wide range of data distributions. A new and independent validation and test set is formed with scene text instances that are out of vocabulary at training time. The competit…
We investigate different approaches to integrating object recognition and planning in a tabletop manipulation domain with the set of objects used in the 2012 RoboCup@Work competition. Results of our preliminary experiments show that, with some approaches, close integration of perception and planning improves the quality of plans, as well as the computation times of feasible plans.
We report generation of a MNIST [4] compatible data set [1] for Tamil vowels to enable building a classification DNN or other such ML/AI deep learning [2] models for Tamil OCR/Handwriting applications. We report the capability of the 60,000 grayscale, 28x28 pixel dataset to build a 92% accuracy (training) and 82% cross-validation 4-layer CNN, with 100,000+ parameters, in TensorFlow. We also report a top-1 classification accuracy of 70% and top-2 classification accuracy of 92% on handwritten vowels showing, for the same network.
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；University Medicine Essen（埃森大学医学院）
When reading images, radiologists generate text reports describing the findings therein. Current state-of-the-art computer-aided diagnosis tools utilize a fixed set of predefined categories automatically extracted from these medical reports for training. This form of supervision limits the potential usage of models as they are unable to pick up on anomalies outside of their predefined set, thus, making it a necessity to retrain the classifier with additional data when faced with novel classes. In contrast, we investigate direct text supervision to break away from this closed set assumption. By…
McMaster University（麦克马斯特大学）；Defence Research and Development Canada（加拿大国防研究与发展部）
Recognition and identification of unknown targets is a crucial task in surveillance and security systems. Electronic Support Measures (ESM) are one of the most effective sensors for identification, especially for maritime and air--to--ground applications. In typical surveillance systems multiple ESM sensors are usually deployed along with kinematic sensors like radar. Different ESM sensors may produce different types of reports ready to be sent to the fusion center. The focus of this paper is to develop a new architecture for target recognition and identification when non--homogeneous ESM and …
We propose a cross-modal co-attention model for continuous emotion recognition using visual-audio-linguistic information. The model consists of four blocks. The visual, audio, and linguistic blocks are used to learn the spatial-temporal features of the multi-modal input. A co-attention block is designed to fuse the learned features with the multi-head co-attention mechanism. The visual encoding from the visual block is concatenated with the attention feature to emphasize the visual information. To make full use of the data and alleviate over-fitting, cross-validation is carried out on the trai…
Team AcieLee: Technical Report for EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023
Southwest University（西南大学）；Samsung Research China-Beijing(SRC-B)（三星中国研究院-北京）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
It has been well proved that deep networks are efficient at extracting features from a given (source) labeled dataset. However, it is not always the case that they can generalize well to other (target) datasets which very often have a different underlying distribution. In this report, we evaluate four different domain adaptation techniques for image classification tasks: DeepCORAL, DeepDomainConfusion, CDAN and CDAN+E. These techniques are unsupervised given that the target dataset dopes not carry any labels during training phase. We evaluate model performance on the office-31 dataset. A link …
In this paper, results of an experimental study of a deep convolution neural network architecture which can classify different handwritten digits using EBLearn library are reported. The purpose of this neural network is to classify input images into 10 different classes or digits (0-9) and to explore new findings. The input dataset used consists of digits images of size 32X32 in grayscale (MNIST dataset).
Technical University of Munich（慕尼黑工业大学）；University of Stuttgart（斯图加特大学）；German Research Center for Artificial Intelligence（德国人工智能研究中心）
Emotional expressions are inherently multimodal -- integrating facial behavior, speech, and gaze -- but their automatic recognition is often limited to a single modality, e.g. speech during a phone call. While previous work proposed crossmodal emotion embeddings to improve monomodal recognition performance, despite its importance, an explicit representation of gaze was not included. We propose a new approach to emotion recognition that incorporates an explicit representation of gaze in a crossmodal emotion embedding framework. We show that our method outperforms the previous state of the art f…
City University of Hong Kong（香港城市大学）；Tsinghua University（清华大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Wuhan University（武汉大学）；ContinualAI Research（ContinualAI研究院）；University of Bologna（博洛尼亚大学）；University of Hamburg（汉堡大学）；Intel Labs（英特尔研究院）
This report summarizes IROS 2019-Lifelong Robotic Vision Competition (Lifelong Object Recognition Challenge) with methods and results from the top $8$ finalists (out of over~$150$ teams). The competition dataset (L)ifel(O)ng (R)obotic V(IS)ion (OpenLORIS) - Object Recognition (OpenLORIS-object) is designed for driving lifelong/continual learning research and application in robotic vision domain, with everyday objects in home, office, campus, and mall scenarios. The dataset explicitly quantifies the variants of illumination, object occlusion, object size, camera-object distance/angles, and clut…
Generative Adversarial Networks (GANs) were proposed in 2014 by Goodfellow et al., and have since been extended into multiple computer vision applications. This report provides a thorough survey of recent GAN research, outlining the various architectures and applications, as well as methods for training GANs and dealing with latent space. This is followed by a discussion of potential areas for future GAN research, including: evaluating GANs, better understanding GANs, and techniques for training GANs. The second part of this report outlines the compilation of a dataset of images `in the wild' …
In this report, an automated bartender system was developed for making orders in a bar using hand gestures. The gesture recognition of the system was developed using Machine Learning techniques, where the model was trained to classify gestures using collected data. The final model used in the system reached an average accuracy of 95%. The system raised ethical concerns both in terms of user interaction and having such a system in a real world scenario, but it could initially work as a complement to a real bartender.
