Image Classification and Video Action Recognition are perhaps the two most foundational tasks in computer vision. Consequently, explaining the inner workings of trained deep neural networks is of prime importance. While numerous efforts focus on explaining the decisions of trained deep neural networks in image classification, exploration in the domain of its temporal version, video action recognition, has been scant. In this work, we take a deeper look at this problem. We begin by revisiting Grad-CAM, one of the popular feature attribution methods for Image Classification, and its extension to Video Action Recognition tasks and examine the method's limitations. To address these, we introduce Video-TCAV, by building on TCAV for Image Classification tasks, which aims to quantify the importance of specific concepts in the decision-making process of Video Action Recognition models. As the scalable generation of concepts is still an open problem, we propose a machine-assisted approach to generate spatial and spatiotemporal concepts relevant to Video Action Recognition for testing Video-TCAV. We then establish the importance of temporally-varying concepts by demonstrating the superiority of dynamic spatiotemporal concepts over trivial spatial concepts. In conclusion, we introduce a framework for investigating hypotheses in action recognition and quantitatively testing them, thus advancing research in the explainability of deep neural networks used in video action recognition.
This paper performs the first investigation into depth for large-scale human action recognition in video where the depth cues are estimated from the videos themselves. We develop a new framework called depth2action and experiment thoroughly into how best to incorporate the depth information. We introduce spatio-temporal depth normalization (STDN) to enforce temporal consistency in our estimated depth sequences. We also propose modified depth motion maps (MDMM) to capture the subtle temporal changes in depth. These two components significantly improve the action recognition performance. We eval…
Exploring Adaptive Masked Reconstruction for Self-Supervised Skeleton-Based Action Recognition
Hefei University of Technology（合肥工业大学）；Jilin University（吉林大学）；Zhejiang Gongshang University（浙江工商大学）；University of Science and Technology of China（中国科学技术大学）
Exploring the Role of Explainability in AI-Assisted Embryo Selection
Barcelona Supercomputing Center（巴塞罗那超级计算中心）；Hospital Clínic de Barcelona（巴塞罗那诊所医院）；Universitat Politécnica de Catalunya - Barcelona TECH（加泰罗尼亚理工大学-巴塞罗那TECH）
Universidad Tecnológica Nacional（国立技术大学）；CONICET（国家科学技术研究委员会）
During recent years transformers architectures have been growing in popularity. Modulated Detection Transformer (MDETR) is an end-to-end multi-modal understanding model that performs tasks such as phase grounding, referring expression comprehension, referring expression segmentation, and visual question answering. One remarkable aspect of the model is the capacity to infer over classes that it was not previously trained for. In this work we explore the use of MDETR in a new task, action detection, without any previous training. We obtain quantitative results using the Atomic Visual Actions dat…
With the growing use of deep learning methods, particularly graph neural networks, which encode intricate interconnectedness information, for a variety of real tasks, there is a necessity for explainability in such settings. In this paper, we demonstrate the applicability of popular explainability approaches on Graph Attention Networks (GAT) for a graph-based super-pixel image classification task. We assess the qualitative and quantitative performance of these techniques on three different datasets and describe our findings. The results shed a fresh light on the notion of explainability in GNN…
A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in such sequential structure offers a fertile ground for building unsupervised learning models. In this paper, we compose a trilogy of exploring the basic and generic supervision in the sequence from spatial, spatiotemporal and sequential perspectives. We materialize the supervisory signals through determining whether a pair of samples is from one frame or from on…
Advancing Vision-based Human Action Recognition: Exploring Vision-Language CLIP Model for Generalisation in Domain-Independent Tasks
Central University of Haryana（哈里亚纳中央大学）；University of New South Wales（新南威尔士大学）；Østfold University College（东福尔大学学院）；Norwegian University of Science and Technology（挪威科技大学）
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究所）；TU Darmstadt（达姆施塔特工业大学）
It is challenging to derive explainability for unsupervised or statistical-based face image quality assessment (FIQA) methods. In this work, we propose a novel set of explainability tools to derive reasoning for different FIQA decisions and their face recognition (FR) performance implications. We avoid limiting the deployment of our tools to certain FIQA methods by basing our analyses on the behavior of FR models when processing samples with different FIQA decisions. This leads to explainability tools that can be applied for any FIQA method with any CNN-based FR solution using activation mappi…
Exploring Self-Attention for Crop-type Classification Explainability
Munich Center for Machine Learning（慕尼黑机器学习中心）；German Federal Ministry of Education and Research（德国联邦教育与研究部）；German Federal Ministry for Economic Affairs and Climate Action（德国联邦经济事务与气候行动部）
Exploring Complementarity and Explainability in CNNs for Periocular Verification Across Acquisition Distances
School of Information Technology Halmstad University, Sweden（信息科技学院 哈姆斯塔德大学，瑞典）；AI Group University of Balearic Islands, Spain（人工智能小组 巴利阿里群岛大学，西班牙）；Faculty of Information Technology（信息科技学院）
National Research Council Canada（加拿大国家研究委员会）；University of Waterloo（滑铁卢大学）
Handwriting recognition technology allows recognizing a written text from a given data. The recognition task can target letters, symbols, or words, and the input data can be a digital image or recorded by various sensors. A wide range of applications from signature verification to electronic document processing can be realized by implementing efficient and accurate handwriting recognition algorithms. Over the years, there has been an increasing interest in experimenting with different types of technology to collect handwriting data, create datasets, and develop algorithms to recognize characte…
Training facial emotion recognition models requires large sets of data and costly annotation processes. To alleviate this problem, we developed a gamified method of acquiring annotated facial emotion data without an explicit labeling effort by humans. The game, which we named Facegame, challenges the players to imitate a displayed image of a face that portrays a particular basic emotion. Every round played by the player creates new data that consists of a set of facial features and landmarks, already annotated with the emotion label of the target facial expression. Such an approach effectively…
The Hong Kong University of Science and Technology（香港科技大学）；University of Technology Sydney（悉尼科技大学）
Contrastive Language-Image Pre-training (CLIP) learns rich representations via readily available supervision of natural language. It improves the performance of downstream vision tasks, including but not limited to the zero-shot, long tail, segmentation, retrieval, caption, and video. However, the visual explainability of CLIP is rarely studied, especially for the raw feature map. To provide visual explanations of its predictions, we propose the Image-Text Similarity Map (ITSM). Based on it, we surprisingly find that CLIP prefers the background regions than the foregrounds, and shows erroneous…
University of Southern California（南加州大学）；Jet Propulsion Laboratory（喷气推进实验室）；California Institute of Technology（加州理工学院）
Deep learning (DL) has proven to be an effective machine learning and computer vision technique. DL-based image segmentation, object recognition and classification will aid many in-situ Mars rover tasks such as path planning and artifact recognition/extraction. However, most of the Deep Neural Network (DNN) architectures are so complex that they are considered a 'black box'. In this paper, we used integrated gradients to describe the attributions of each neuron to the output classes. It provides a set of explainability tools (ET) that opens the black box of a DNN so that the individual contrib…
National Agriculture and Food Research Organization (NARO)（国立农业与食品研究机构（NARO））
Agricultural image recognition tasks are becoming increasingly dependent on deep learning (DL); however, despite the excellent performance of DL, it is difficult to comprehend the type of logic or features of the input image it uses during decision making. Knowing the logic or features is highly crucial for result verification, algorithm improvement, training data improvement, and knowledge extraction. However, the explanations from the current heatmap-based algorithms are insufficient for the abovementioned requirements. To address this, this paper details the development of a classification …
University of Science and Technology of China（中国科学技术大学）
Facial Expression Recognition (FER) is an important task in computer vision and has wide applications in human-computer interaction, intelligent security, emotion analysis, and other fields. However, the limited size of FER datasets limits the generalization ability of expression recognition models, resulting in ineffective model performance. To address this problem, we propose a semi-supervised learning framework that utilizes unlabeled face data to train expression recognition models effectively. Our method uses a dynamic threshold module (\textbf{DTM}) that can adaptively adjust the confide…
Recent work has shown that self-attention can serve as a basic building block for image recognition models. We explore variations of self-attention and assess their effectiveness for image recognition. We consider two forms of self-attention. One is pairwise self-attention, which generalizes standard dot-product attention and is fundamentally a set operator. The other is patchwise self-attention, which is strictly more powerful than convolution. Our pairwise self-attention networks match or outperform their convolutional counterparts, and the patchwise models substantially outperform the convo…
Can Large Language Models Grasp Event Signals? Exploring Pure Zero-Shot Event-based Recognition
School of Computer and Artificial Intelligence（计算机与人工智能学院）；Beijing Technology and Business University（北京工商大学）；School of Computer Science（计算机科学学院）；The University of Sydney（悉尼大学）
University of Science and Technology of China（中国科学技术大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）
The audio-video based emotion recognition aims to classify a given video into basic emotions. In this paper, we describe our approaches in EmotiW 2019, which mainly explores emotion features and feature fusion strategies for audio and visual modality. For emotion features, we explore audio feature with both speech-spectrogram and Log Mel-spectrogram and evaluate several facial features with different CNN models and different emotion pretrained strategies. For fusion strategies, we explore intra-modal and cross-modal fusion methods, such as designing attention mechanisms to highlights important…
Zhejiang University（浙江大学）；Rochester Institute of Technology（罗切斯特理工学院）；ETH Zurich（苏黎世联邦理工学院）
We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most classic and simple classifiers. Current deep models learn the classifier in a fully parametric manner, ignoring the latent data structure and lacking simplicity and explainability. DNC instead conducts nonparametric, case-based reasoning; it utilizes sub-centroids of training samples to describe class distributions and clearly explains the classification as the proximity of test data and the class sub-centroids in…
With the proposition of neural networks for point clouds, deep learning has started to shine in the field of 3D object recognition while researchers have shown an increased interest to investigate the reliability of point cloud networks by adversarial attacks. However, most of the existing studies aim to deceive humans or defense algorithms, while the few that address the operation principles of the models themselves remain flawed in terms of critical point selection. In this work, we propose two adversarial methods: One Point Attack (OPA) and Critical Traversal Attack (CTA), which incorporate…
Whilst face recognition applications are becoming increasingly prevalent within our daily lives, leading approaches in the field still suffer from performance bias to the detriment of some racial profiles within society. In this study, we propose a novel adversarial derived data augmentation methodology that aims to enable dataset balance at a per-subject level via the use of image-to-image transformation for the transfer of sensitive racial characteristic facial features. Our aim is to automatically construct a synthesised dataset by transforming facial images across varying racial domains, w…
University of Science and Technology of China（中国科学技术大学）
Current works formulate facial action unit (AU) recognition as a supervised learning problem, requiring fully AU-labeled facial images during training. It is challenging if not impossible to provide AU annotations for large numbers of facial images. Fortunately, AUs appear on all facial images, whether manually labeled or not, satisfy the underlying anatomic mechanisms and human behavioral habits. In this paper, we propose a deep semi-supervised framework for facial action unit recognition from partially AU-labeled facial images. Specifically, the proposed deep semi-supervised AU recognition a…
There is a big difference in the tone of color of skin between dark and light skinned people. Despite this fact, most face recognition tasks almost all classical state-of-the-art models are trained on datasets containing an overwhelming majority of light skinned face images. It is tedious to collect a huge amount of data for dark skinned faces and train a model from scratch. In this paper, we apply transfer learning on VGGFace to check how it works on recognising dark skinned mainly Ethiopian faces. The dataset is of low quality and low resource. Our experimental results show above 95\% accura…
Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）
Scene text recognition (STR) has been extensively studied in last few years. Many recently-proposed methods are specially designed to accommodate the arbitrary shape, layout and orientation of scene texts, but ignoring that various font (or writing) styles also pose severe challenges to STR. These methods, where font features and content features of characters are tangled, perform poorly in text recognition on scene images with texts in novel font styles. To address this problem, we explore font-independent features of scene texts via attentional generation of glyphs in a large number of font …
State-of-the-art deep face recognition approaches report near perfect performance on popular benchmarks, e.g., Labeled Faces in the Wild. However, their performance deteriorates significantly when they are applied on low quality images, such as those acquired by surveillance cameras. A further challenge for low resolution face recognition for surveillance applications is the matching of recorded low resolution probe face images with high resolution reference images, which could be the case in watchlist scenarios. In this paper, we have addressed these problems and investigated the factors that…
Crime and Security Research Institute（犯罪与安全研究所）；Cardiff University（卡迪夫大学）；School of Engineering（工程学院）
The popularity of Deep Learning for real-world applications is ever-growing. With the introduction of high performance hardware, applications are no longer limited to image recognition. With the introduction of more complex problems comes more and more complex solutions, and the increasing need for explainable AI. Deep Neural Networks for Video tasks are amongst the most complex models, with at least twice the parameters of their Image counterparts. However, explanations for these models are often ill-adapted to the video domain. The current work in explainability for video models is still ove…
Facebook AI Research (FAIR)（Facebook人工智能研究院（FAIR））
Neural networks for image recognition have evolved through extensive manual design from simple chain-like models to structures with multiple wiring paths. The success of ResNets and DenseNets is due in large part to their innovative wiring plans. Now, neural architecture search (NAS) studies are exploring the joint optimization of wiring and operation types, however, the space of possible wirings is constrained and still driven by manual design despite being searched. In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks. To do…
NAVER Clova；KAIST（韩国科学技术院）；NAVER AI Lab（NAVER人工智能实验室）；Yonsei University（延世大学）
Data augmentation has recently emerged as an essential component of modern training recipes for visual recognition tasks. However, data augmentation for video recognition has been rarely explored despite its effectiveness. Few existing augmentation recipes for video recognition naively extend the image augmentation methods by applying the same operations to the whole video frames. Our main idea is that the magnitude of augmentation operations for each frame needs to be changed over time to capture the real-world video's temporal variations. These variations should be generated as diverse as po…
The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models with a text prompt. However, the zero-shot use of CLIP is unstable with respect to the phrasing of the input text, making it necessary to carefully engineer the prompts used. We find that this instability stems from a selective similarity score, which is based only on a subset of the semantically meaningful input tokens. To mitigate it, we present a novel ex…
Laboratoire de recherche en Imagerie et Orthopédie (LIO)（影像与骨科研究实验室（LIO））；TÉLUQ University（加拿大远程大学）
The emergence of RGB-D sensors offered new possibilities for addressing complex artificial vision problems efficiently. Human posture recognition is among these computer vision problems, with a wide range of applications such as ambient assisted living and intelligent health care systems. In this context, our paper presents novel methods and ideas to design automatic posture recognition systems using an RGB-D camera. More specifically, we introduce two supervised methods to learn and recognize human postures using the main types of visual data provided by an RGB-D camera. The first method is b…
The University of Tokyo（东京大学）；University of Strasbourg（斯特拉斯堡大学）；Harima mental clinic（播磨精神诊所）
How to handle gender with machine learning is a controversial topic. A growing critical body of research brought attention to the numerous issues transgender communities face with the adoption of current automatic gender recognition (AGR) systems. In contrast, we explore how such technologies could potentially be appropriated to support transgender practices and needs, especially in non-Western contexts like Japan. We designed a virtual makeup probe to assist transgender individuals with passing, that is to be perceived as the gender they identify as. To understand how such an application migh…
In this paper, we present a process to investigate the effects of transfer learning for automatic facial expression recognition from emotions to pain. To this end, we first train a VGG16 convolutional neural network to automatically discern between eight categorical emotions. We then fine-tune successively larger parts of this network to learn suitable representations for the task of automatic pain recognition. Subsequently, we apply those fine-tuned representations again to the original task of emotion recognition to further investigate the differences in performance between the models. In th…
Spiru Haret University of Bucharest（布加勒斯特斯皮鲁·哈雷特大学）；University of Bath（巴斯大学）
A new approach in iris recognition based on Circular Fuzzy Iris Segmentation (CFIS) and Gabor Analytic Iris Texture Binary Encoder (GAITBE) is proposed and tested here. CFIS procedure is designed to guarantee that similar iris segments will be obtained for similar eye images, despite the fact that the degree of occlusion may vary from one image to another. Its result is a circular iris ring (concentric with the pupil) which approximates the actual iris. GAITBE proves better encoding of statistical independence between the iris codes extracted from different irides using Hilbert Transform. Irid…
The Hong Kong University of Science and Technology（香港科技大学）；The Hong Kong University of Science and Technology Shenzhen Research Institute（香港科技大学深圳研究院）
Automatic surgical phase recognition plays a vital role in robot-assisted surgeries. Existing methods ignored a pivotal problem that surgical phases should be classified by learning segment-level semantics instead of solely relying on frame-wise information. This paper presents a segment-attentive hierarchical consistency network (SAHC) for surgical phase recognition from videos. The key idea is to extract hierarchical high-level semantic-consistent segments and use them to refine the erroneous predictions caused by ambiguous frames. To achieve it, we design a temporal hierarchical network to …
