There exists a widely accepted set of assertions in the digital image and video coding literature, which are as follows: the Human Visual System (HVS) is more sensitive to luminance (often confused with brightness) than photon energies (often confused with chromaticity and chrominance). Passages similar to the following occur with high frequency in the peer reviewed literature and academic text books: "the HVS is much more sensitive to brightness than colour" and/or "the HVS is much more sensitive to luma than chroma". In this discussion paper, a Visible Light-Based Human Visual System (VL-HVS) conceptual model is discussed. The objectives of VL-HVS are as follows: 1. To provide a deeper theoretical reflection of the fundamental relationship between visible light, the manifestation of colour perception derived from visible light and the physiology of the perception of colour. That is, in terms of the physics of visible light, photobiology and the human subjective interpretation of visible light, it is appropriate to provide comprehensive background information in relation to the natural interactions between visible light, the retinal photoreceptors and the subsequent cortical processing of such. 2. To provide a more wholesome account with respect to colour information in digital image and video processing applications. 3. To recontextualise colour data in the RGB and YCbCr colour spaces, such that novel techniques in digital image and video processing, including quantisation and artifact reduction techniques, may be developed based on both luma and chroma information (not luma data only).
VicKAM: Visual Conceptual Knowledge Guided Action Map for Weakly Supervised Group Activity Recognition
School of Information Science and Technology, Beijing University of Technology（北京工业大学信息科学与技术学院）；Institute of automation, Chinese Academy of Science（中国科学院自动化研究所）
University of Maryland（马里兰大学）；Facebook AI Research（脸书人工智能研究院）；Georgia Tech（佐治亚理工学院）
We ask the question: to what extent can recent large-scale language and image generation models blend visual concepts? Given an arbitrary object, we identify a relevant object and generate a single-sentence description of the blend of the two using a language model. We then generate a visual depiction of the blend using a text-based image generation model. Quantitative and qualitative evaluations demonstrate the superiority of language models over classical methods for conceptual blending, and of recent large-scale image generation models over prior models for the visual depiction.
The availability of large-scale image captioning and visual question answering datasets has contributed significantly to recent successes in vision-and-language pre-training. However, these datasets are often collected with overrestrictive requirements inherited from their original target tasks (e.g., image caption generation), which limit the resulting dataset scale and diversity. We take a step further in pushing the limits of vision-and-language pre-training data by relaxing the data collection pipeline used in Conceptual Captions 3M (CC3M) [Sharma et al. 2018] and introduce the Conceptual …
Conceptual Codebook Learning for Vision-Language Models
Harbin Institute of Technology（哈尔滨工业大学）；Southern University of Science and Technology（南方科技大学）；University of California San Diego（加利福尼亚大学圣迭戈分校）；University of Missouri（密苏里大学）
Peking University（北京大学）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Peng Cheng Laboratory（鹏城实验室）；City University of Hong Kong（香港城市大学）；Communication University of China（中国传媒大学）
Existing compression methods typically focus on the removal of signal-level redundancies, while the potential and versatility of decomposing visual data into compact conceptual components still lack further study. To this end, we propose a novel conceptual compression framework that encodes visual data into compact structure and texture representations, then decodes in a deep synthesis fashion, aiming to achieve better visual reconstruction quality, flexible content manipulation, and potential support for various vision tasks. In particular, we propose to compress images by a dual-layered mode…
MambaTrans: Multimodal Fusion Image Translation via Large Language Model Priors for Downstream Visual Tasks
School of Physics and Optoelectronic Engineering（物理与光电工程学院）；Guangdong-HongKong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology（粤港澳联合智能微纳光电技术实验室）；School of Information Engineering and Automation（信息工程与自动化学院）
本文提出MambaTrans，一种多模态融合图像模态翻译器，利用多模态大语言模型描述和语义分割掩码作为输入，通过Multi-Model State Space Block捕获跨模态依赖，在不调整预训练模型参数的情况下提升下游视觉任务性能。
Stealthy in Semantics, Antagonistic in Space: Attacking Visible-Infrared Object Detectors via Object-Level Misalignment
Beijing University of Technology（北京工业大学）；Peking University（北京大学）；National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所空间集成信息系统全国重点实验室）；Intelligent Science & Technology Academy of CASIC（中国航天科工集团智能科技研究院）
Zhejiang University（浙江大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Multi-spectral sensors consisting of a standard (visible-light) camera and a long-wave infrared camera can simultaneously provide both visible and thermal images. Since thermal images are independent from environmental illumination, they can help to overcome certain limitations of standard cameras under complicated illumination conditions. However, due to the difference in the information source of the two types of cameras, their images usually share very low texture similarity. Hence, traditional texture-based feature matching methods cannot be directly applied to obtain stereo correspondence…
Deep learning is a rapidly developing approach in the field of infrared and visible image fusion. In this context, the use of dense blocks in deep networks significantly improves the utilization of shallow information, and the combination of the Generative Adversarial Network (GAN) also improves the fusion performance of two source images. We propose a new method based on dense blocks and GANs , and we directly insert the input image-visible light image in each layer of the entire network. We use SSIM and gradient loss functions that are more consistent with perception instead of mean square e…
Hierarchical Semantic-Visual Fusion of Visible and Near-infrared Images for Long-range Haze Removal
National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（多光谱信息智能处理技术国家实验室，人工智能与自动化学院，华中科技大学）；State Key Laboratory of Dynamic Optical Imaging and Measurement（动态光学成像与测量国家重点实验室）
University of Michigan（密歇根大学）；Princeton University（普林斯顿大学）
We consider the task of identifying human actions visible in online videos. We focus on the widely spread genre of lifestyle vlogs, which consist of videos of people performing actions while verbally describing them. Our goal is to identify if actions mentioned in the speech description of a video are visually present. We construct a dataset with crowdsourced manual annotations of visible actions, and introduce a multimodal algorithm that leverages information derived from visual and linguistic clues to automatically infer which actions are visible in a video. We demonstrate that our multimoda…
LIGM, École des Ponts, Univ Gustave Eiffel, CNRS（LIGM实验室、巴黎综合理工学院、古斯塔夫·埃菲尔大学、法国国家科学研究中心）；IMS, University of Bordeaux, Bordeaux INP, CNRS（IMS实验室、波尔多大学、波尔多国立理工学院、法国国家科学研究中心）
Given a pair of partially overlapping source and target images and a keypoint in the source image, the keypoint's correspondent in the target image can be either visible, occluded or outside the field of view. Local feature matching methods are only able to identify the correspondent's location when it is visible, while humans can also hallucinate its location when it is occluded or outside the field of view through geometric reasoning. In this paper, we bridge this gap by training a network to output a peaked probability distribution over the correspondent's location, regardless of this corre…
MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement
Electronic Information School, Wuhan University, China（武汉大学电子信息学院）；Suzhou Institute of Wuhan University, China（武汉大学苏州研究院）；School of Automation, Wuhan University, China（武汉大学自动化学院）
Visual object tracking, as a fundamental task in computer vision, has drawn much attention in recent years. To extend trackers to a wider range of applications, researchers have introduced information from multiple modalities to handle specific scenes, which is a promising research prospect with emerging methods and benchmarks. To provide a thorough review of multi-modal track-ing, we summarize the multi-modal tracking algorithms, especially visible-depth (RGB-D) tracking and visible-thermal (RGB-T) tracking in a unified taxonomy from different aspects. Second, we provide a detailed descriptio…
EPOFusion: Exposure aware Progressive Optimization Method for Infrared and Visible Image Fusion
College of Information Engineering, Zhejiang University of Technology（浙江工业大学信息工程学院）；College of Information Science and Technology, Zhejiang Shuren University（浙江树人大学信息科技学院）；Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电机电子工程系）
With an ever-widening domain of aerial robotic applications, including many mission critical tasks such as disaster response operations, search and rescue missions and infrastructure inspections taking place in GPS-denied environments, the need for reliable autonomous operation of aerial robots has become crucial. Operating in GPS-denied areas aerial robots rely on a multitude of sensors to localize and navigate. Visible spectrum cameras are the most commonly used sensors due to their low cost and weight. However, in environments that are visually-degraded such as in conditions of poor illumin…
Whiting School of Engineering, Johns Hopkins University（约翰斯·霍普金斯大学怀廷工程学院）
Synthesis of face images from visual attributes is an important problem in computer vision and biometrics due to its applications in law enforcement and entertainment. Recent advances in deep generative networks have made it possible to synthesize high-quality face images from visual attributes. However, existing methods are specifically designed for generating unimodal images (i.e visible faces) from attributes. In this paper, we propose a novel generative adversarial network that simultaneously synthesizes identity preserving multimodal face images (i.e. visible, sketch, thermal, etc.) from …
FusionRegister: Every Infrared and Visible Image Fusion Deserves Registration
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China（江南大学人工智能与计算机科学学院）；School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou, China（苏州科技大学电子与信息工程学院）
Dalian University of Technology（大连理工大学）；Peng Cheng Laboratory（鹏城实验室）
This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Aiming at generating an image of high visual quality, previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. These approaches neglect that modality differences implying the complementary information are extremely important for both fusion and subsequent detection task. This paper proposes a bilevel optimization formulation for the joint problem of fusion and detection, and then unrolls to…
UCLA（加州大学洛杉矶分校）；Stanford University（斯坦福大学）；MIT BCS, CBMM, CSAIL（麻省理工学院脑与认知科学系、心智/大脑/机器研究中心、计算机科学与人工智能实验室）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
A critical aspect of human visual perception is the ability to parse visual scenes into individual objects and further into object parts, forming part-whole hierarchies. Such composite structures could induce a rich set of semantic concepts and relations, thus playing an important role in the interpretation and organization of visual signals as well as for the generalization of visual perception and reasoning. However, existing visual reasoning benchmarks mostly focus on objects rather than parts. Visual reasoning based on the full part-whole hierarchy is much more challenging than object-cent…
Infrared and Visible Image Fusion Based on Implicit Neural Representations
College of Computer Science, Beijing Information Science and Technology University（北京信息科技大学计算机学院）；School of Mathematical Sciences, Capital Normal University（首都师范大学数学学院）
Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning
Shanghai Jiao Tong University（上海交通大学）；ZhongguanCun Academy（中关村学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai University（上海大学）；City University of Hong Kong（香港城市大学）；Wuhan University（武汉大学）
The Bag--of--Visual--Words (BoVW) is a visual description technique that aims at shortening the semantic gap by partitioning a low--level feature space into regions of the feature space that potentially correspond to visual concepts and by giving more value to this space. In this paper we present a conceptual analysis of three major properties of language grammar and how they can be adapted to the computer vision and image understanding domain based on the bag of visual words paradigm. Evaluation of the visual grammar shows that a positive impact on classification accuracy and/or descriptor si…
University of Rome, Tor Vergata（罗马第二大学）；Istituto di Bioimmagini e Fisiologia Molecolare, CNR（意大利国家研究委员会生物成像与分子生理学研究所）；Martinos Center for Biomedical Imaging（马丁诺斯生物医学成像中心）；MGH（麻省总医院）；Harvard Medical School（哈佛医学院）
Brain decoding is a field of computational neuroscience that uses measurable brain activity to infer mental states or internal representations of perceptual inputs. Therefore, we propose a novel approach to brain decoding that also relies on semantic and contextual similarity. We employ an fMRI dataset of natural image vision and create a deep learning decoding pipeline inspired by the existence of both bottom-up and top-down processes in human vision. We train a linear brain-to-feature model to map fMRI activity features to visual stimuli features, assuming that the brain projects visual info…
Infrared and Visible Image Fusion with Hierarchical Human Perception
School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）；Key Laboratory of Image Cognition, Chongqing University of Posts and Telecommunications（重庆邮电大学图像认知重点实验室）
SFDFusion: An Efficient Spatial-Frequency Domain Fusion Network for Infrared and Visible Image Fusion
Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能学院）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）
Infrared and visible image fusion has been a hot issue in image fusion. In this task, a fused image containing both the gradient and detailed texture information of visible images as well as the thermal radiation and highlighting targets of infrared images is expected to be obtained. In this paper, a novel Bayesian fusion model is established for infrared and visible images. In our model, the image fusion task is cast into a regression problem. To measure the variable uncertainty, we formulate the model in a hierarchical Bayesian manner. Aiming at making the fused image satisfy human visual sy…
Suzhou University of Science and Technology（苏州科技大学）；Jiangnan University（江南大学）
Background: Leaning redundant and complementary relationships is a critical step in the human visual system. Inspired by the infrared cognition ability of crotalinae animals, we design a joint convolution auto-encoder (JCAE) network for infrared and visible image fusion. Methods: Our key insight is to feed infrared and visible pair images into the network simultaneously and separate an encoder stream into two private branches and one common branch, the private branch works for complementary features learning and the common branch does for redundant features learning. We also build two fusion r…
Unmanned Aerial Vehicles (UAV) can pose a major risk for aviation safety, due to both negligent and malicious use. For this reason, the automated detection and tracking of UAV is a fundamental task in aerial security systems. Common technologies for UAV detection include visible-band and thermal infrared imaging, radio frequency and radar. Recent advances in deep neural networks (DNNs) for image-based object detection open the possibility to use visual information for this detection and tracking task. Furthermore, these detection architectures can be implemented as backbones for visual trackin…
In many practical applications of long-range imaging such as biometrics and surveillance, thermal imagining modalities are often used to capture images in low-light and nighttime conditions. However, such imaging systems often suffer from atmospheric turbulence, which introduces severe blur and deformation artifacts to the captured images. Such an issue is unavoidable in long-range imaging and significantly decreases the face verification accuracy. In this paper, we first investigate the problem with a turbulence simulation method on real-world thermal images. An end-to-end reconstruction meth…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；MIT BCS, CBMM, CSAIL（麻省理工学院脑与认知科学系、大脑、心智与机器中心、计算机科学与人工智能实验室）
We present a meta-learning framework for learning new visual concepts quickly, from just one or a few examples, guided by multiple naturally occurring data streams: simultaneously looking at images, reading sentences that describe the objects in the scene, and interpreting supplemental sentences that relate the novel concept with other concepts. The learned concepts support downstream applications, such as answering questions by reasoning about unseen images. Our model, namely FALCON, represents individual visual concepts, such as colors and shapes, as axis-aligned boxes in a high-dimensional …
Harvard University（哈佛大学）；Augsburg University（奥格斯堡大学）；Technische Universität München（慕尼黑工业大学）；Ludwig-Maximilians-Universität München（慕尼黑大学）
Making inferences from partial information constitutes a critical aspect of cognition. During visual perception, pattern completion enables recognition of poorly visible or occluded objects. We combined psychophysics, physiology and computational models to test the hypothesis that pattern completion is implemented by recurrent computations and present three pieces of evidence that are consistent with this hypothesis. First, subjects robustly recognized objects even when rendered <15% visible, but recognition was largely impaired when processing was interrupted by backward masking. Second, inva…
Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation
Columbia University（哥伦比亚大学）；University of Washington（华盛顿大学）
