Image Captioning via Compact Bidirectional Architecture
School of Big Data and Statistics, Anhui University（安徽大学大数据与统计学院）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）；Intelligent Interconnected Systems Laboratory of Anhui Province (Hefei University of Technology)（安徽省智能互联系统实验室（合肥工业大学））；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息学院）；JD Explore Academy, JD.com Inc（京东探索研究院）；State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science and Technology（安徽理工大学深部煤矿采动响应与灾害防控国家重点实验室）
Most current image captioning models typically generate captions from left-to-right. This unidirectional property makes them can only leverage past context but not future context. Though refinement-based models can exploit both past and future context by generating a new caption in the second stage based on pre-retrieved or pre-generated captions in the first stage, the decoder of these models generally consists of two networks~(i.e. a retriever or captioner in the first stage and a captioner in the second stage), which can only be executed sequentially. In this paper, we introduce a Compact Bidirectional Transformer model for image captioning that can leverage bidirectional context implicitly and explicitly while the decoder can be executed parallelly. Specifically, it is implemented by tightly coupling left-to-right(L2R) and right-to-left(R2L) flows into a single compact model to serve as a regularization for implicitly exploiting bidirectional context and optionally allowing explicit interaction of the bidirectional flows, while the final caption is chosen from either L2R or R2L flow in a sentence-level ensemble manner. We conduct extensive ablation studies on MSCOCO benchmark and find that the compact bidirectional architecture and the sentence-level ensemble play more important roles than the explicit interaction mechanism. By combining with word-level ensemble seamlessly, the effect of sentence-level ensemble is further enlarged. We further extend the conventional one-flow self-critical training to the two-flows version under this architecture and achieve new state-of-the-art results in comparison with non-vision-language-pretraining models. Finally, we verify the generality of this compact bidirectional architecture by extending it to LSTM backbone. Source code is available at https://github.com/YuanEZhou/cbtic.
We develop the first approximate inference algorithm for 1-Best (and M-Best) decoding in bidirectional neural sequence models by extending Beam Search (BS) to reason about both forward and backward time dependencies. Beam Search (BS) is a widely used approximate inference algorithm for decoding sequences from unidirectional neural sequence models. Interestingly, approximate inference in bidirectional models remains an open problem, despite their significant advantage in modeling information from both the past and future. To enable the use of bidirectional models, we present Bidirectional Beam …
Hasso Plattner Institute, University of Potsdam（哈索·普拉特纳研究所，波茨坦大学）
This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning. Our model builds on a deep convolutional neural network (CNN) and two separate LSTM networks. It is capable of learning long term visual-language interactions by making use of history and future context information at high level semantic space. Two novel deep bidirectional variant models, in which we increase the depth of nonlinearity transition in different way, are proposed to learn hierarchical visual-language embeddings. Data augmentation techniques such as multi-crop, mu…
ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning
Keio University（庆应义塾大学）；National Institute of Informatics（国立信息学研究所）；National Institute of Informatics Research and Development Center for Large Language Models（国立信息学研究所大型语言模型研发中心）
Institute of Computer Science and Technology, Peking University（北京大学计算机科学技术研究所）
Video captioning aims to automatically generate natural language descriptions of video content, which has drawn a lot of attention recent years. Generating accurate and fine-grained captions needs to not only understand the global content of video, but also capture the detailed object information. Meanwhile, video representations have great impact on the quality of generated captions. Thus, it is important for video captioning to capture salient objects with their detailed temporal dynamics, and represent them using discriminative spatio-temporal representations. In this paper, we propose a ne…
South China University of Technology（华南理工大学）；Tencent AI Lab（腾讯人工智能实验室）
Dense video captioning is a newly emerging task that aims at both localizing and describing all events in a video. We identify and tackle two challenges on this task, namely, (1) how to utilize both past and future contexts for accurate event proposal predictions, and (2) how to construct informative input to the decoder for generating natural event descriptions. First, previous works predominantly generate temporal event proposals in the forward direction, which neglects future video context. We propose a bidirectional proposal method that effectively exploits both past and future contexts to…
University of Electronic Science and Technology（电子科技大学）；The University of Queensland（昆士兰大学）
Video captioning has been attracting broad research attention in multimedia community. However, most existing approaches either ignore temporal information among video frames or just employ local contextual temporal knowledge. In this work, we propose a novel video captioning framework, termed as \emph{Bidirectional Long-Short Term Memory} (BiLSTM), which deeply captures bidirectional global temporal structure in video. Specifically, we first devise a joint visual modelling approach to encode video data by combining a forward LSTM pass, a backward LSTM pass, together with visual features from …
School of Remote Sensing and Information Engineering, Wuhan University（武汉大学遥感信息工程学院）
Adversarial learning has shown its advances in generating natural and diverse descriptions in image captioning. However, the learned reward of existing adversarial methods is vague and ill-defined due to the reward ambiguity problem. In this paper, we propose a refined Adversarial Inverse Reinforcement Learning (rAIRL) method to handle the reward ambiguity problem by disentangling reward for each word in a sentence, as well as achieve stable adversarial training by refining the loss function to shift the generator towards Nash equilibrium. In addition, we introduce a conditional term in the lo…
In this paper we study a brand new topic of interactive image captioning with human in the loop. Different from automated image captioning where a given test image is the sole input in the inference stage, we have access to both the test image and a sequence of (incomplete) user-input sentences in the interactive scenario. We formulate the problem as Visually Conditioned Sentence Completion (VCSC). For VCSC, we propose asynchronous bidirectional decoding for image caption completion (ABD-Cap). With ABD-Cap as the core module, we build iCap, a web-based interactive image captioning system capab…
Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder-decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to be deployed on embedded system with limited hardware resources. This is because the size of word and output embedding matrices grow proportionally with the size of vocabulary, adversely affecting the compactness of these networks. To address this limitation, this paper introduces a brand new idea in the domain of image captioning. That is, we tackle the problem o…
Recent research that applies Transformer-based architectures to image captioning has resulted in state-of-the-art image captioning performance, capitalising on the success of Transformers on natural language tasks. Unfortunately, though these models work well, one major flaw is their large model sizes. To this end, we present three parameter reduction methods for image captioning Transformers: Radix Encoding, cross-layer parameter sharing, and attention parameter sharing. By combining these methods, our proposed ACORT models have 3.7x to 21.6x fewer parameters than the baseline model without c…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Image captioning is one of the most challenging tasks in AI, which aims to automatically generate textual sentences for an image. Recent methods for image captioning follow encoder-decoder framework that transforms the sequence of salient regions in an image into natural language descriptions. However, these models usually lack the comprehensive understanding of the contextual interactions reflected on various visual relationships between objects. In this paper, we explore explicit and implicit visual relationships to enrich region-level representations for image captioning. Explicitly, we bui…
Technical University of Munich（慕尼黑工业大学）；Meta AI；Simon Fraser University（西蒙菲莎大学）
Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly task-specific neural modules, it remains understudied how to explicitly depict their shared nature to learn them simultaneously. In this work, we propose UniT3D, a simple yet effective fully unified transformer-based architecture for jointly solving 3D visual grounding and dense captioning. UniT3D enables learning a strong multimodal representation across the two tasks…
Conventional methods for the image-text generation tasks mainly tackle the naturally bidirectional generation tasks separately, focusing on designing task-specific frameworks to improve the quality and fidelity of the generated samples. Recently, Vision-Language Pre-training models have greatly improved the performance of the image-to-text generation tasks, but large-scale pre-training models for text-to-image synthesis task are still under-developed. In this paper, we propose ERNIE-ViLG, a unified generative pre-training framework for bidirectional image-text generation with transformer model…
Recent video and language pretraining frameworks lack the ability to generate sentences. We present Multimodal Video Generative Pretraining (MV-GPT), a new pretraining framework for learning from unlabelled videos which can be effectively used for generative tasks such as multimodal video captioning. Unlike recent video-language pretraining frameworks, our framework trains both a multimodal video encoder and a sentence decoder jointly. To overcome the lack of captions in unlabelled videos, we leverage the future utterance as an additional text source and propose a bidirectional generation obje…
University of Michigan（密歇根大学）；Microsoft Research（微软研究院）；Microsoft Cloud & AI（微软云与人工智能部门）；Microsoft AI & Research（微软人工智能与研究部门）
This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models. The unified VLP model is pre-trained on a large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequ…
Dalian University of Technology（大连理工大学）；Mila（米拉）；McGill University（麦吉尔大学）
Image captioning is a research hotspot where encoder-decoder models combining convolutional neural network (CNN) and long short-term memory (LSTM) achieve promising results. Despite significant progress, these models generate sentences differently from human cognitive styles. Existing models often generate a complete sentence from the first word to the end, without considering the influence of the following words on the whole sentence generation. In this paper, we explore the utilization of a human-like cognitive style, i.e., building overall cognition for the image to be described and the sen…
Along with the prosperity of recurrent neural network in modelling sequential data and the power of attention mechanism in automatically identify salient information, image captioning, a.k.a., image description, has been remarkably advanced in recent years. Nonetheless, most existing paradigms may suffer from the deficiency of invariance to images with different scaling, rotation, etc.; and effective integration of standalone attention to form a holistic end-to-end system. In this paper, we propose a novel image captioning architecture, termed Recurrent Image Captioner (\textbf{RIC}), which al…
Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning
Beijing University of Technology（北京理工大学）；Shanghai Jiao Tong University（上海交通大学）；Chinese Academy of Sciences（中国科学院）；The Hong Kong Polytechnic University（香港理工大学）
Incorporating granularity bias as the margin into contrastive loss for video captioning
The School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；The School of Aeronautics and Astronautics, University of Electronic Science and Technology of China（电子科技大学航空航天学院）
针对视频描述中短语长尾分布导致的粒度偏差问题，提出基于统计的偏差提取器量化偏差影响，并将粒度偏差作为间隔融入双向三元组对比损失（GMC Loss），为头部和尾部句子建立不同训练目标，在 MSRVTT 和 MSVD 上达到 SOTA 性能。
Recently, much advance has been made in image captioning, and an encoder-decoder framework has been adopted by all the state-of-the-art models. Under this framework, an input image is encoded by a convolutional neural network (CNN) and then translated into natural language with a recurrent neural network (RNN). The existing models counting on this framework merely employ one kind of CNNs, e.g., ResNet or Inception-X, which describe image contents from only one specific view point. Thus, the semantic meaning of an input image cannot be comprehensively understood, which restricts the performance…
University of Chinese Academy of Science（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Harbin Institute of Technology, Weihai（哈尔滨工业大学（威海））
In video captioning task, the best practice has been achieved by attention-based models which associate salient visual components with sentences in the video. However, existing study follows a common procedure which includes a frame-level appearance modeling and motion modeling on equal interval frame sampling, which may bring about redundant visual information, sensitivity to content noise and unnecessary computation cost. We propose a plug-and-play PickNet to perform informative frame picking in video captioning. Based on a standard Encoder-Decoder framework, we develop a reinforcement-learn…
PIGEONS: Incremental Long-Video Captioning with Persistent Identity Gallery and Evolving Overarching Narrative Summary
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；The Hong Kong University of Science and Technology（香港科技大学）；Peking University（北京大学）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Nanjing University（南京大学）
Recent years have witnessed the rapid progress of image captioning. However, the demands for large memory storage and heavy computational burden prevent these captioning models from being deployed on mobile devices. The main obstacles lie in the heavyweight visual feature extractors (i.e., object detectors) and complicated cross-modal fusion networks. To this end, we propose LightCap, a lightweight image captioner for resource-limited devices. The core design is built on the recent CLIP model for efficient image captioning. To be specific, on the one hand, we leverage the CLIP model to extract…
Regional Attention-Enhanced Swin Transformer for Clinically Relevant Medical Image Captioning
Electrical Engineering and Computer Science（电子工程与计算机科学）；Gwangju Institute of Science and Technology（全州科学技术研究院）；Electrical and Computer Engineering Department（电子与计算机工程系）；Chonnam National University（全南国立大学）；AI Convergence Department（人工智能融合部门）；Department of Information Systems, CCSIT（信息系统系，CCSIT）；King Faisal University（国王费萨尔大学）；Thomas Jefferson University, Philadelphia（费城托马斯杰斐逊大学）
Automatic generation of video captions is a fundamental challenge in computer vision. Recent techniques typically employ a combination of Convolutional Neural Networks (CNNs) and Recursive Neural Networks (RNNs) for video captioning. These methods mainly focus on tailoring sequence learning through RNNs for better caption generation, whereas off-the-shelf visual features are borrowed from CNNs. We argue that careful designing of visual features for this task is equally important, and present a visual feature encoding technique to generate semantically rich captions using Gated Recurrent Units …
We do not speak word by word from scratch; our brain quickly structures a pattern like \textsc{sth do sth at someplace} and then fill in the detailed descriptions. To render existing encoder-decoder image captioners such human-like reasoning, we propose a novel framework: learning to Collocate Neural Modules (CNM), to generate the `inner pattern' connecting visual encoder and language decoder. Unlike the widely-used neural module networks in visual Q\&A, where the language (ie, question) is fully observable, CNM for captioning is more challenging as the language is being generated and thus is …
CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning
Tsinghua University（清华大学）；University of Science and Technology of China（中国科学技术大学）；Microsoft（微软）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Innovation Institute（上海创新研究院）；Alibaba Cloud（阿里云）；The Chinese University of Hong Kong（香港中文大学）
Good Representation, Better Explanation: Role of Convolutional Neural Networks in Transformer-Based Remote Sensing Image Captioning
Department of Computer Science and Engineering（计算机科学与工程系）；Indian Institute of Technology, Roorkee（印度理工学院拉胡尔分校）；Department of Mechanical Engineering（机械工程系）；Indian Institute of Technology, BHU（印度理工学院BHU分校）；Department of Information Technology（信息技术系）；National Institute of Technology, Srinagar（国家理工学院斯里 Nagar分校）
Image captioning has demonstrated models that are capable of generating plausible text given input images or videos. Further, recent work in image generation has shown significant improvements in image quality when text is used as a prior. Our work ties these concepts together by creating an architecture that can enable bidirectional generation of images and text. We call this network Multi-Modal Vector Representation (MMVR). Along with MMVR, we propose two improvements to the text conditioned image generation. Firstly, a n-gram metric based cost function is introduced that generalizes the cap…
In this paper, we propose a single UniFied transfOrmer (UFO), which is capable of processing either unimodal inputs (e.g., image or language) or multimodal inputs (e.g., the concatenation of the image and the question), for vision-language (VL) representation learning. Existing approaches typically design an individual network for each modality and/or a specific fusion network for multimodal tasks. To simplify the network architecture, we use a single transformer network and enforce multi-task learning during VL pre-training, which includes the image-text contrastive loss, image-text matching …
Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy
School of Geodesy and Geomatics, Wuhan University（武汉大学测绘学院）；Hubei Luojia Laboratory（湖北珞珈实验室）；School of Architecture and Urban Planning, Shenzhen University（深圳大学建筑与城市规划学院）
Grounded Situation Recognition (GSR) aims to generate structured semantic summaries of images for "human-like" event understanding. Specifically, GSR task not only detects the salient activity verb (e.g. buying), but also predicts all corresponding semantic roles (e.g. agent and goods). Inspired by object detection and image captioning tasks, existing methods typically employ a two-stage framework: 1) detect the activity verb, and then 2) predict semantic roles based on the detected verb. Obviously, this illogical framework constitutes a huge obstacle to semantic understanding. First, pre-dete…
Dense captioning is a newly emerging computer vision topic for understanding images with dense language descriptions. The goal is to densely detect visual concepts (e.g., objects, object parts, and interactions between them) from images, labeling each with a short descriptive phrase. We identify two key challenges of dense captioning that need to be properly addressed when tackling the problem. First, dense visual concept annotations in each image are associated with highly overlapping target regions, making accurate localization of each visual concept challenging. Second, the large amount of …
The workflow of extracting features from images using convolutional neural networks (CNN) and generating captions with recurrent neural networks (RNN) has become a de-facto standard for image captioning task. However, since CNN features are originally designed for classification task, it is mostly concerned with the main conspicuous element of the image, and often fails to correctly convey information on local, secondary elements. We propose to incorporate coding with vector of locally aggregated descriptors (VLAD) on spatial pyramid for CNN features of sub-regions in order to generate image r…
HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning
College of Computer Science, Inner Mongolia University（内蒙古大学计算机学院）；Research Center for Spatiotemporal Intelligence, Inner Mongolia University（内蒙古大学时空智能研究中心）；Department of Aerospace Intelligent Science and Technology, School of Astronautics, Beihang University（北航宇航学院航空航天智能科学与技术系）；State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北航虚拟现实技术与系统国家重点实验室）；China Mobile Communications Group Inner Mongolia Co., Ltd.（中国移动通信集团内蒙古有限公司）
School of Informatics and Computing（信息学与计算学院）；Indiana University（印第安纳大学）
Recent work in computer vision has yielded impressive results in automatically describing images with natural language. Most of these systems generate captions in a sin- gle language, requiring multiple language-specific models to build a multilingual captioning system. We propose a very simple technique to build a single unified model across languages, using artificial tokens to control the language, making the captioning system more compact. We evaluate our approach on generating English and Japanese captions, and show that a typical neural captioning architecture is capable of learning a si…
Lifelogging cameras capture everyday life from a first-person perspective, but generate so much data that it is hard for users to browse and organize their image collections effectively. In this paper, we propose to use automatic image captioning algorithms to generate textual representations of these collections. We develop and explore novel techniques based on deep learning to generate captions for both individual images and image streams, using temporal consistency constraints to create summaries that are both more compact and less noisy. We evaluate our techniques with quantitative and qua…
BiSegMamba: Efficient Bidirectional Tri-Oriented Mamba for 3D Medical Image Segmentation
School of Computer Science and Engineering, Beihang University（北航计算机科学与工程学院）；State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北航虚拟现实技术与系统国家重点实验室）
