Studies of image captioning are shifting towards a trend of a fully end-to-end paradigm by leveraging powerful visual pre-trained models and transformer-based generation architecture for more flexible model training and faster inference speed. State-of-the-art approaches simply extract isolated concepts or attributes to assist description generation. However, such approaches do not consider the hierarchical semantic structure in the textual domain, which leads to an unpredictable mapping between visual representations and concept words. To this end, we propose a novel Progressive Tree-Structured prototype Network (dubbed PTSN), which is the first attempt to narrow down the scope of prediction words with appropriate semantics by modeling the hierarchical textual semantics. Specifically, we design a novel embedding method called tree-structured prototype, producing a set of hierarchical representative embeddings which capture the hierarchical semantic structure in textual space. To utilize such tree-structured prototypes into visual cognition, we also propose a progressive aggregation module to exploit semantic relationships within the image and prototypes. By applying our PTSN to the end-to-end captioning framework, extensive experiments conducted on MSCOCO dataset show that our method achieves a new state-of-the-art performance with 144.2% (single model) and 146.5% (ensemble of 4 models) CIDEr scores on `Karpathy' split and 141.4% (c5) and 143.9% (c40) CIDEr scores on the official online test server. Trained models and source code have been released at: https://github.com/NovaMind-Z/PTSN.
University of Chinese Academy of Sciences（中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）；Huawei Technologies（华为技术有限公司）
Dense video captioning (DVC) aims to generate multi-sentence descriptions to elucidate the multiple events in the video, which is challenging and demands visual consistency, discoursal coherence, and linguistic diversity. Existing methods mainly generate captions from individual video segments, lacking adaptation to the global visual context and progressive alignment between the fast-evolved visual content and textual descriptions, which results in redundant and spliced descriptions. In this paper, we introduce the concept of information flow to model the progressive information changing acros…
Video captioning has shown impressive progress in recent years. One key reason of the performance improvements made by existing methods lie in massive paired video-sentence data, but collecting such strong annotation, i.e., high-quality sentences, is time-consuming and laborious. It is the fact that there now exist an amazing number of videos with weak annotation that only contains semantic concepts such as actions and objects. In this paper, we investigate using weak annotation instead of strong annotation to train a video captioning model. To this end, we propose a progressive visual reasoni…
City University of Hong Kong（香港城市大学）；Fuzhou University（福州大学）
Automatically evaluating the quality of image captions can be very challenging since human language is quite flexible that there can be various expressions for the same meaning. Most of the current captioning metrics rely on token level matching between candidate caption and the ground truth label sentences. It usually neglects the sentence-level information. Motivated by the auto-encoder mechanism and contrastive representation learning advances, we propose a learning-based metric for image captioning, which we call Intrinsic Image Captioning Evaluation($I^2CE$). We develop three progressive …
In this paper, we propose a novel conditional-generative-adversarial-nets-based image captioning framework as an extension of traditional reinforcement-learning (RL)-based encoder-decoder architecture. To deal with the inconsistent evaluation problem among different objective language metrics, we are motivated to design some "discriminator" networks to automatically and progressively determine whether generated caption is human described or machine generated. Two kinds of discriminator architectures (CNN and RNN-based structures) are introduced since each has its own advantages. The proposed a…
The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning
School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Macquarie University（麦考瑞大学）；Australian Institute for Machine Learning, The University of Adelaide（阿德莱德大学澳大利亚机器学习研究所）
ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
University of Science and Technology of China（中国科学技术大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
Most current image captioning systems focus on describing general image content, and lack background knowledge to deeply understand the image, such as exact named entities or concrete events. In this work, we focus on the entity-aware news image captioning task which aims to generate informative captions by leveraging the associated news articles to provide background knowledge about the target image. However, due to the length of news articles, previous works only employ news articles at the coarse article or sentence level, which are not fine-grained enough to refine relevant events and choo…
Astrea: A MOE-based Visual Understanding Model with Progressive Alignment
Zhejiang University（浙江大学）；Southern University of Science and Technology（南方科技大学）；Beijing University of Technology（北京工业大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Hong Kong Polytechnic University（香港理工大学）；Qingdao University（青岛大学）
We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In contrast to manually annotating all the training samples, separately collecting uni-modal datasets is immensely easier, e.g., a large-scale image dataset and a sentence dataset. We leverage such massive unpaired image and caption data upon standard paired data by learning to associate them. To this end, our proposed semi-supervised learning method assigns pseud…
Tencent Data Platform（腾讯数据平台）；University of Science and Technology of China（中国科学技术大学）
Generalized Zero-Shot Learning (GZSL) aims to recognize new categories with auxiliary semantic information,e.g., category attributes. In this paper, we handle the critical issue of domain shift problem, i.e., confusion between seen and unseen categories, by progressively improving cross-domain transferability and category discriminability of visual representations. Our approach, named Dual Progressive Prototype Network (DPPN), constructs two types of prototypes that record prototypical visual patterns for attributes and categories, respectively. With attribute prototypes, DPPN alternately sear…
MovieTeller: Tool-augmented Movie Synopsis with ID Consistent Progressive Abstraction
Central Universities（中央高校）；National Natural Science Foundation of China（中国国家自然科学基金委员会）；Research Fund for International Scientists of National Natural Science Foundation of China（中国国家自然科学基金委员会国际科学家研究基金）
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for AI（Vector人工智能研究所）；Canada CIFAR AI Chair（加拿大CIFAR人工智能讲席）
The problem of language grounding has attracted much attention in recent years due to its pivotal role in more general image-lingual high level reasoning tasks (e.g., image captioning, VQA). Despite the tremendous progress in visual grounding, the performance of most approaches has been hindered by the quality of bounding box proposals obtained in the early stages of all recent pipelines. To address this limitation, we propose a general progressive query-guided bounding box refinement architecture (OptiBox) that leverages global image encoding for added context. We apply this architecture in t…
Existing image captioning systems are dedicated to generating narrative captions for images, which are spatially detached from the image in presentation. However, texts can also be used as decorations on the image to highlight the key points and increase the attractiveness of images. In this work, we introduce a new task called captioning on image (CapOnImage), which aims to generate dense captions at different locations of the image based on contextual information. To fully exploit the surrounding visual context to generate the most suitable caption for each location, we propose a multi-modal…
Renmin University of China（中国人民大学）；INRIA（法国国家信息与自动化研究所）
Video paragraph captioning aims to describe multiple events in untrimmed videos with descriptive paragraphs. Existing approaches mainly solve the problem in two steps: event detection and then event captioning. Such two-step manner makes the quality of generated paragraphs highly dependent on the accuracy of event proposal detection which is already a challenging task. In this paper, we propose a paragraph captioning model which eschews the problematic event detection stage and directly generates paragraphs for untrimmed videos. To describe coherent and diverse events, we propose to enhance th…
ProCNS: Progressive Prototype Calibration and Noise Suppression for Weakly-Supervised Medical Image Segmentation
Southern University of Science and Technology（南方科技大学）；University of Hong Kong（香港大学）；Jiaxing Research Institute, Southern University of Science and Technology（南方科技大学嘉兴研究院）
Jarvis Research Center, Tencent YouTu Lab（腾讯优图实验室贾维斯研究中心）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究所）
Beijing Jiaotong University（北京交通大学）；University of Rochester（罗切斯特大学）
Zero-Shot Learning (ZSL) has received extensive attention and successes in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. Key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary semantic prototypes (e.g., word or attribute vectors). However, the popularly learned projection functions in previous works cannot generalize well due to non-visual components included in semantic prototypes. Besides, the incompleteness of provided prototypes and captured images has less been considered by the state-of-the-art approac…
Active learning is a promising alternative to alleviate the issue of high annotation cost in the computer vision tasks by consciously selecting more informative samples to label. Active learning for object detection is more challenging and existing efforts on it are relatively rare. In this paper, we propose a novel hybrid approach to address this problem, where the instance-level uncertainty and diversity are jointly considered in a bottom-up manner. To balance the computational complexity, the proposed approach is designed as a two-stage procedure. At the first stage, an Entropy-based Non-Ma…
Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation
School of Computer Science and Cyber Engineering, Guangzhou University（计算机科学与网络安全学院，广州大学）；Guangdong Key Laboratory of Intelligent Information Processing, College of Electronics and Information Engineering, Shenzhen University（智能信息处理重点实验室，电子与信息工程学院，深圳大学）；School of Electronics and Communication Engineering, Guangzhou University（电子与通信工程学院，广州大学）；Univ Rennes, INSA Rennes, CNRS, IETR - UMR 6164（里昂大学，INSA里昂，CNRS，IETR - UMR 6164）；Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen Key Laboratory of Advanced Machine Learning and Applications, Institute of Artificial Intelligence and Advanced Communication, College of Electronics and Information Engineering, Shenzhen University（智能信息处理重点实验室，先进机器学习与应用重点实验室，人工智能与高级通信研究所，电子与信息工程学院，深圳大学）；College of Mathematics and Statistics, Shenzhen University（数学与统计学院，深圳大学）
Beijing Jiaotong University（北京交通大学）；Hefei University of Technology（合肥工业大学）
Generalized Zero-Shot Learning (GZSL) identifies unseen categories by knowledge transferred from the seen domain, relying on the intrinsic interactions between visual and semantic information. Prior works mainly localize regions corresponding to the sharing attributes. When various visual appearances correspond to the same attribute, the sharing attributes inevitably introduce semantic ambiguity, hampering the exploration of accurate semantic-visual interactions. In this paper, we deploy the dual semantic-visual transformer module (DSVTM) to progressively model the correspondences between attr…
Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究院）；Shanghai Innovation Institute（上海创新研究院）；School of Informatics, Xiamen University（厦门大学信息学院）；East China Normal University（华东师范大学）
Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction
Shenzhen University（深圳大学）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院）；School of Biomedical Engineering and Informatics, Nanjing Medical University（南京医科大学生物医学工程与信息学院）；National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University（深圳大学大数据系统计算技术国家工程实验室）
Sun Yat-sen University（中山大学）；JD Explore Academy（京东探索研究院）
Recent advances on text-to-image generation have witnessed the rise of diffusion models which act as powerful generative models. Nevertheless, it is not trivial to exploit such latent variable models to capture the dependency among discrete words and meanwhile pursue complex visual-language alignment in image captioning. In this paper, we break the deeply rooted conventions in learning Transformer-based encoder-decoder, and propose a new diffusion model based paradigm tailored for image captioning, namely Semantic-Conditional Diffusion Networks (SCD-Net). Technically, for each input image, we …
Zhejiang University（浙江大学）；Tianjin University（天津大学）；University of Warwick（华威大学）；Binghamton University（宾汉姆顿大学）
We introduce a simple yet effective episode-based training framework for zero-shot learning (ZSL), where the learning system requires to recognize unseen classes given only the corresponding class semantics. During training, the model is trained within a collection of episodes, each of which is designed to simulate a zero-shot classification task. Through training multiple episodes, the model progressively accumulates ensemble experiences on predicting the mimetic unseen classes, which will generalize well on the real unseen classes. Based on this training framework, we propose a novel generat…
The virtual try-on system has gained great attention due to its potential to give customers a realistic, personalized product presentation in virtualized settings. In this paper, we present PT-VTON, a novel pose-transfer-based framework for cloth transfer that enables virtual try-on with arbitrary poses. PT-VTON can be applied to the fashion industry within minimal modification of existing systems while satisfying the overall visual fashionability and detailed fabric appearance requirements. It enables efficient clothes transferring between model and user images with arbitrary pose and body sh…
Beijing Jiaotong University（北京交通大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Zero-shot learning (ZSL) has received increasing attention in recent years especially in areas of fine-grained object recognition, retrieval, and image captioning. The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors. However, the popularly learned projection functions in previous works cannot generalize well since they assume the distribution consistency between seen and unseen domains at sample-level.Besides, the provided non-visual and unique class attributes can significantly degrade the recognition performance in semantic space.…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Amazon Prime Video（亚马逊Prime Video）
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To address this challenge, we introduce a novel training framework based on cross-modal contrastive learning that uses progressive self-distillation and soft image-text alignments to more efficiently learn robust representations from noisy data. Our model distills its own knowledge to dynamically generate soft-alignment targets for a subset of images and captio…
Northwestern Polytechnical University（西北工业大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Few-shot semantic segmentation aims to segment the target objects in query under the condition of a few annotated support images. Most previous works strive to mine more effective category information from the support to match with the corresponding objects in query. However, they all ignored the category information gap between query and support images. If the objects in them show large intra-class diversity, forcibly migrating the category information from the support to the query is ineffective. To solve this problem, we are the first to introduce an intermediate prototype for mining both d…
3D dense captioning is a recently-proposed novel task, where point clouds contain more geometric information than the 2D counterpart. However, it is also more challenging due to the higher complexity and wider variety of inter-object relations contained in point clouds. Existing methods only treat such relations as by-products of object feature learning in graphs without specifically encoding them, which leads to sub-optimal results. In this paper, aiming at improving 3D dense captioning via capturing and utilizing the complex relations in the 3D scene, we propose MORE, a Multi-Order RElation …
School of Electrical & Information Engineering, University of the Witwatersrand（威特沃特斯兰德大学电气与信息工程学院）
This paper presents deformable templates as a tool for segmentation and localization of biological structures in medical images. Structures are represented by a prototype template, combined with a parametric warp mapping used to deform the original shape. The localization procedure is achieved using a multi-stage, multi-resolution algorithm de-signed to reduce computational complexity and time. The algorithm initially identifies regions in the image most likely to contain the desired objects and then examines these regions at progressively increasing resolutions. The final stage of the algorit…
Prototype-Guided Curriculum Learning for Zero-Shot Learning
School of Electronic Information and Communications, Huazhong University of Science and Technology（电子信息与通信学院，华中科技大学）；Mohamed bin Zayed University of AI（马尔代夫人工智能大学）；School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学）；School of Computer Science, The University of Sydney（计算机科学学院，悉尼大学）
Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method
MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统实验室）；Institute of Microelectronics, University of Chinese Academy of Sciences（中国科学院大学微电子学院）；School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences（中国科学院大学前沿交叉科学学院）
