Our winning entry for the CVPR 2023 Generic Event Boundary Captioning (GEBC) competition is detailed in this paper. Unlike conventional video captioning tasks, GEBC demands that the captioning model possess an understanding of immediate changes in status around the designated video boundary, making it a difficult task. This paper proposes an effective model LLMVA-GEBC (Large Language Model with Video Adapter for Generic Event Boundary Captioning): (1) We utilize a pretrained LLM for generating human-like captions with high quality. (2) To adapt the model to the GEBC task, we take the video Q-former as an adapter and train it with the frozen visual feature extractors and LLM. Our proposed method achieved a 76.14 score on the test set and won the first place in the challenge. Our code is available at https://github.com/zjr2000/LLMVA-GEBC .
Multimodal learning on video and text data has been receiving growing attention from many researchers in various research tasks, including text-to-video retrieval, video-to-text retrieval, and video captioning. Although many algorithms have been proposed for those challenging tasks, most of them are developed on English language datasets. Despite Indonesian being one of the most spoken languages in the world, the research progress on the multimodal video-text with Indonesian sentences is still under-explored, likely due to the absence of the public benchmark dataset. To address this issue, we construct the first public Indonesian video-text dataset by translating English sentences from the MSVD dataset to Indonesian sentences. Using our dataset, we then train neural network models which were developed for the English video-text dataset on three tasks, i.e., text-to-video retrieval, video-to-text retrieval, and video captioning. The recent neural network-based approaches to video-text tasks often utilized a feature extractor that is primarily pretrained on an English vision-language dataset. Since the availability of the pretraining resources with Indonesian sentences is relatively limited, the applicability of those approaches to our dataset is still questionable. To overcome the lack of pretraining resources, we apply cross-lingual transfer learning by utilizing the feature extractors pretrained on the English dataset, and we then fine-tune the models on our Indonesian dataset. Our experimental results show that this approach can help to improve the performance for the three tasks on all metrics. Finally, we discuss potential future works using our dataset, inspiring further research in the Indonesian multimodal video-text tasks. We believe that our dataset and our experimental results could provide valuable contributions to the community. Our dataset is available on GitHub.
Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields. Deep neural networks are the dominant methods, offering state-of-the-art performance. However, these methods are often undeployable in low-power devices like smartphones due to the large size of the model parameters. In this paper, we propose to exploit simple pooling front-end and down-sampling algorithms with knowledge distillation for audio and visual attributes using a reduced number of audio-visual frames. With the help of knowledge distillation from the teacher model, our proposed method greatly reduces the redundant information in audio-visual streams without losing critical contexts for caption generation. Extensive experimental evaluations on the MSR-VTT dataset demonstrate that our proposed approach significantly reduces the inference time by about 80% with a small sacrifice (less than 0.02%) in captioning accuracy.
Due to the limited scale and quality of video-text training corpus, most vision-language foundation models employ image-text datasets for pretraining and primarily focus on modeling visually semantic representations while disregarding temporal semantic representations and correlations. To address this issue, we propose COSA, a COncatenated SAmple pretrained vision-language foundation model. COSA jointly models visual contents and event-level temporal cues using only image-text corpora. We achieve this by sequentially concatenating multiple image-text pairs as inputs for pretraining. This transformation effectively converts existing image-text corpora into a pseudo long-form video-paragraph corpus, enabling richer scene transformations and explicit event-description correspondence. Extensive experiments demonstrate that COSA consistently improves performance across a broad range of downstream tasks, including long-form/short-form video-text tasks and image-text tasks such as retrieval, captioning, and question answering. Notably, COSA achieves state-of-the-art results on various competitive benchmarks. Code and model are released at https://github.com/TXH-mercury/COSA.
To promote the development of Vision-Language Pre-training (VLP) and multimodal Large Language Model (LLM) in the Chinese community, we firstly release the largest public Chinese high-quality video-language dataset named Youku-mPLUG, which is collected from Youku, a well-known Chinese video-sharing website, with strict criteria of safety, diversity, and quality. Youku-mPLUG contains 10 million Chinese video-text pairs filtered from 400 million raw videos across a wide range of 45 diverse categories for large-scale pre-training. In addition, to facilitate a comprehensive evaluation of video-language models, we carefully build the largest human-annotated Chinese benchmarks covering three popular video-language tasks of cross-modal retrieval, video captioning, and video category classification. Youku-mPLUG can enable researchers to conduct more in-depth multimodal research and develop better applications in the future. Furthermore, we release popular video-language pre-training models, ALPRO and mPLUG-2, and our proposed modularized decoder-only model mPLUG-video pre-trained on Youku-mPLUG. Experiments show that models pre-trained on Youku-mPLUG gain up to 23.1% improvement in video category classification. Besides, mPLUG-video achieves a new state-of-the-art result on these benchmarks with 80.5% top-1 accuracy in video category classification and 68.9 CIDEr score in video captioning, respectively. Finally, we scale up mPLUG-video based on the frozen Bloomz with only 1.7% trainable parameters as Chinese multimodal LLM, and demonstrate impressive instruction and video understanding ability. The zero-shot instruction understanding experiment indicates that pretraining with Youku-mPLUG can enhance the ability to comprehend overall and detailed visual semantics, recognize scene text, and leverage open-domain knowledge.
We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. PaLI-X advances the state-of-the-art on most vision-and-language benchmarks considered (25+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.
To help the visually impaired enjoy movies, automatic movie narrating systems are expected to narrate accurate, coherent, and role-aware plots when there are no speaking lines of actors. Existing works benchmark this challenge as a normal video captioning task via some simplifications, such as removing role names and evaluating narrations with ngram-based metrics, which makes it difficult for automatic systems to meet the needs of real application scenarios. To narrow this gap, we construct a large-scale Chinese movie benchmark, named Movie101. Closer to real scenarios, the Movie Clip Narrating (MCN) task in our benchmark asks models to generate role-aware narration paragraphs for complete movie clips where no actors are speaking. External knowledge, such as role information and movie genres, is also provided for better movie understanding. Besides, we propose a new metric called Movie Narration Score (MNScore) for movie narrating evaluation, which achieves the best correlation with human evaluation. Our benchmark also supports the Temporal Narration Grounding (TNG) task to investigate clip localization given text descriptions. For both two tasks, our proposed methods well leverage external knowledge and outperform carefully designed baselines. The dataset and codes are released at https://github.com/yuezih/Movie101.
Large-scale image-text contrastive pre-training models, such as CLIP, have been demonstrated to effectively learn high-quality multimodal representations. However, there is limited research on learning video-text representations for general video multimodal tasks based on these powerful features. Towards this goal, we propose a novel video-text pre-training method dubbed VLAB: Video Language pre-training by feature Adapting and Blending, which transfers CLIP representations to video pre-training tasks and develops unified video multimodal models for a wide range of video-text tasks. Specifically, VLAB is founded on two key strategies: feature adapting and feature blending. In the former, we introduce a new video adapter module to address CLIP's deficiency in modeling temporal information and extend the model's capability to encompass both contrastive and generative tasks. In the latter, we propose an end-to-end training method that further enhances the model's performance by exploiting the complementarity of image and video features. We validate the effectiveness and versatility of VLAB through extensive experiments on highly competitive video multimodal tasks, including video text retrieval, video captioning, and video question answering. Remarkably, VLAB outperforms competing methods significantly and sets new records in video question answering on MSRVTT, MSVD, and TGIF datasets. It achieves an accuracy of 49.6, 61.0, and 79.0, respectively. Codes and models will be released.
Automatically narrating videos in natural language complying with user requests, i.e. Controllable Video Captioning task, can help people manage massive videos with desired intentions. However, existing works suffer from two shortcomings: 1) the control signal is single-grained which can not satisfy diverse user intentions; 2) the video description is generated in a single round which can not be further edited to meet dynamic needs. In this paper, we propose a novel \textbf{V}ideo \textbf{C}aption \textbf{E}diting \textbf{(VCE)} task to automatically revise an existing video description guided by multi-grained user requests. Inspired by human writing-revision habits, we design the user command as a pivotal triplet \{\textit{operation, position, attribute}\} to cover diverse user needs from coarse-grained to fine-grained. To facilitate the VCE task, we \textit{automatically} construct an open-domain benchmark dataset named VATEX-EDIT and \textit{manually} collect an e-commerce dataset called EMMAD-EDIT. We further propose a specialized small-scale model (i.e., OPA) compared with two generalist Large Multi-modal Models to perform an exhaustive analysis of the novel task. For evaluation, we adopt comprehensive metrics considering caption fluency, command-caption consistency, and video-caption alignment. Experiments reveal the task challenges of fine-grained multi-modal semantics understanding and processing. Our datasets, codes, and evaluation tools are available at https://github.com/yaolinli/VCE.
We propose a new two-stage pre-training framework for video-to-text generation tasks such as video captioning and video question answering: A generative encoder-decoder model is first jointly pre-trained on massive image-text data to learn fundamental vision-language concepts, and then adapted to video data in an intermediate video-text pre-training stage to learn video-specific skills such as spatio-temporal reasoning. As a result, our VideoOFA model achieves new state-of-the-art performance on four Video Captioning benchmarks, beating prior art by an average of 9.7 points in CIDEr score. It also outperforms existing models on two open-ended Video Question Answering datasets, showcasing its generalization capability as a universal video-to-text model.
Humans can naturally reason from superficial state differences (e.g. ground wetness) to transformations descriptions (e.g. raining) according to their life experience. In this paper, we propose a new visual reasoning task to test this transformation reasoning ability in real-world scenarios, called \textbf{V}isual \textbf{T}ransformation \textbf{T}elling (VTT). Given a series of states (i.e. images), VTT requires to describe the transformation occurring between every two adjacent states. Different from existing visual reasoning tasks that focus on surface state reasoning, the advantage of VTT is that it captures the underlying causes, e.g. actions or events, behind the differences among states. We collect a novel dataset to support the study of transformation reasoning from two existing instructional video datasets, CrossTask and COIN, comprising 13,547 samples. Each sample involves the key state images along with their transformation descriptions. Our dataset covers diverse real-world activities, providing a rich resource for training and evaluation. To construct an initial benchmark for VTT, we test several models, including traditional visual storytelling methods (CST, GLACNet, Densecap) and advanced multimodal large language models (LLaVA v1.5-7B, Qwen-VL-chat, Gemini Pro Vision, GPT-4o, and GPT-4). Experimental results reveal that even state-of-the-art models still face challenges in VTT, highlighting substantial areas for improvement.
With the development of Vision-Language Pre-training Models (VLPMs) represented by CLIP and ALIGN, significant breakthroughs have been achieved for association-based visual tasks such as image classification and image-text retrieval by the zero-shot capability of CLIP without fine-tuning. However, CLIP is hard to apply to generation-based tasks. This is due to the lack of decoder architecture and pre-training tasks for generation. Although previous works have created generation capacity for CLIP through additional language models, a modality gap between the CLIP representations of different modalities and the inability of CLIP to model the offset of this gap, which fails the concept to transfer across modalities. To solve the problem, we try to map images/videos to the language modality and generate captions from the language modality. In this paper, we propose the K-nearest-neighbor Cross-modality Mapping (Knight), a zero-shot method from association to generation. With text-only unsupervised training, Knight achieves State-of-the-Art performance in zero-shot methods for image captioning and video captioning. Our code is available at https://github.com/junyangwang0410/Knight.
With the widespread popularity of user-generated short videos, it becomes increasingly challenging for content creators to promote their content to potential viewers. Automatically generating appealing titles and covers for short videos can help grab viewers' attention. Existing studies on video captioning mostly focus on generating factual descriptions of actions, which do not conform to video titles intended for catching viewer attention. Furthermore, research for cover selection based on multimodal information is sparse. These problems motivate the need for tailored methods to specifically support the joint task of short video title generation and cover selection (TG-CS) as well as the demand for creating corresponding datasets to support the studies. In this paper, we first collect and present a real-world dataset named Short Video Title Generation (SVTG) that contains videos with appealing titles and covers. We then propose a Title generation and Cover selection with attention Refinement (TCR) method for TG-CS. The refinement procedure progressively selects high-quality samples and highly relevant frames and text tokens within each sample to refine model training. Extensive experiments show that our TCR method is superior to various existing video captioning methods in generating titles and is able to select better covers for noisy real-world short videos.
Video captioning (VC) is a fast-moving, cross-disciplinary area of research that bridges work in the fields of computer vision, natural language processing (NLP), linguistics, and human-computer interaction. In essence, VC involves understanding a video and describing it with language. Captioning is used in a host of applications from creating more accessible interfaces (e.g., low-vision navigation) to video question answering (V-QA), video retrieval and content generation. This survey covers deep learning-based VC, including but, not limited to, attention-based architectures, graph networks, reinforcement learning, adversarial networks, dense video captioning (DVC), and more. We discuss the datasets and evaluation metrics used in the field, and limitations, applications, challenges, and future directions for VC.
In this paper, we propose a Vision-Audio-Language Omni-peRception pretraining model (VALOR) for multi-modal understanding and generation. Different from widely-studied vision-language pretraining models, VALOR jointly models relationships of vision, audio and language in an end-to-end manner. It contains three separate encoders for single modality representations, and a decoder for multimodal conditional text generation. We design two pretext tasks to pretrain VALOR model, including Multimodal Grouping Alignment (MGA) and Multimodal Grouping Captioning (MGC). MGA projects vision, language and audio to the same common space, building vision-language, audio-language and audiovisual-language alignment simultaneously. MGC learns how to generate text tokens in conditions of vision, audio or their both. To promote vision-audio-language pretraining research, we construct a large-scale high-quality tri-modality dataset named VALOR-1M, which contains 1M audiable videos with human annotated audiovisual captions. Extensive experiments show that VALOR can learn strong multimodal correlations and be generalized to various downstream tasks (e.g., retrieval, captioning and question answering), with different input modalities (e.g., vision-language, audio-language and audiovisual-language). VALOR achieves new state-of-the-art performances on series of public cross-modality benchmarks. Code and data are available at project page https://casia-iva-group.github.io/projects/VALOR.
Supervised approaches for learning spatio-temporal scene graphs (STSG) from video are greatly hindered due to their reliance on STSG-annotated videos, which are labor-intensive to construct at scale. Is it feasible to instead use readily available video captions as weak supervision? To address this question, we propose LASER, a neuro-symbolic framework to enable training STSG generators using only video captions. LASER employs large language models to first extract logical specifications with rich spatio-temporal semantic information from video captions. LASER then trains the underlying STSG generator to align the predicted STSG with the specification. The alignment algorithm overcomes the challenges of weak supervision by leveraging a differentiable symbolic reasoner and using a combination of contrastive, temporal, and semantics losses. The overall approach efficiently trains low-level perception models to extract a fine-grained STSG that conforms to the video caption. In doing so, it enables a novel methodology for learning STSGs without tedious annotations. We evaluate our method on three video datasets: OpenPVSG, 20BN, and MUGEN. Our approach demonstrates substantial improvements over fully-supervised baselines, achieving a unary predicate prediction accuracy of 27.78% (+12.65%) and a binary recall@5 of 0.42 (+0.22) on OpenPVSG. Additionally, LASER exceeds baselines by 7% on 20BN and 5.2% on MUGEN in terms of overall predicate prediction accuracy.
Soccer is more than just a game - it is a passion that transcends borders and unites people worldwide. From the roar of the crowds to the excitement of the commentators, every moment of a soccer match is a thrill. Yet, with so many games happening simultaneously, fans cannot watch them all live. Notifications for main actions can help, but lack the engagement of live commentary, leaving fans feeling disconnected. To fulfill this need, we propose in this paper a novel task of dense video captioning focusing on the generation of textual commentaries anchored with single timestamps. To support this task, we additionally present a challenging dataset consisting of almost 37k timestamped commentaries across 715.9 hours of soccer broadcast videos. Additionally, we propose a first benchmark and baseline for this task, highlighting the difficulty of temporally anchoring commentaries yet showing the capacity to generate meaningful commentaries. By providing broadcasters with a tool to summarize the content of their video with the same level of engagement as a live game, our method could help satisfy the needs of the numerous fans who follow their team but cannot necessarily watch the live game. We believe our method has the potential to enhance the accessibility and understanding of soccer content for a wider audience, bringing the excitement of the game to more people.
Video captioning aims to convey dynamic scenes from videos using natural language, facilitating the understanding of spatiotemporal information within our environment. Although there have been recent advances, generating detailed and enriched video descriptions continues to be a substantial challenge. In this work, we introduce Video ChatCaptioner, an innovative approach for creating more comprehensive spatiotemporal video descriptions. Our method employs a ChatGPT model as a controller, specifically designed to select frames for posing video content-driven questions. Subsequently, a robust algorithm is utilized to answer these visual queries. This question-answer framework effectively uncovers intricate video details and shows promise as a method for enhancing video content. Following multiple conversational rounds, ChatGPT can summarize enriched video content based on previous conversations. We qualitatively demonstrate that our Video ChatCaptioner can generate captions containing more visual details about the videos. The code is publicly available at https://github.com/Vision-CAIR/ChatCaptioner
Scaling up weakly-supervised datasets has shown to be highly effective in the image-text domain and has contributed to most of the recent state-of-the-art computer vision and multimodal neural networks. However, existing large-scale video-text datasets and mining techniques suffer from several limitations, such as the scarcity of aligned data, the lack of diversity in the data, and the difficulty of collecting aligned data. Currently popular video-text data mining approach via automatic speech recognition (ASR) used in HowTo100M provides low-quality captions that often do not refer to the video content. Other mining approaches do not provide proper language descriptions (video tags) and are biased toward short clips (alt text). In this work, we show how recent advances in image captioning allow us to pre-train high-quality video models without any parallel video-text data. We pre-train several video captioning models that are based on an OPT language model and a TimeSformer visual backbone. We fine-tune these networks on several video captioning datasets. First, we demonstrate that image captioning pseudolabels work better for pre-training than the existing HowTo100M ASR captions. Second, we show that pre-training on both images and videos produces a significantly better network (+4 CIDER on MSR-VTT) than pre-training on a single modality. Our methods are complementary to the existing pre-training or data mining approaches and can be used in a variety of settings. Given the efficacy of the pseudolabeling method, we are planning to publicly release the generated captions.
The development of language models have moved from encoder-decoder to decoder-only designs. In addition, we observe that the two most popular multimodal tasks, the generative and contrastive tasks, are nontrivial to accommodate in one architecture, and further need adaptations for downstream tasks. We propose a novel paradigm of training with a decoder-only model for multimodal tasks, which is surprisingly effective in jointly learning of these disparate vision-language tasks. This is done with a simple model, called MaMMUT. It consists of a single vision encoder and a text decoder, and is able to accommodate contrastive and generative learning by a novel two-pass approach on the text decoder. We demonstrate that joint learning of these diverse objectives is simple, effective, and maximizes the weight-sharing of the model across these tasks. Furthermore, the same architecture enables straightforward extensions to open-vocabulary object detection and video-language tasks. The model tackles a diverse range of tasks, while being modest in capacity. Our model achieves the state of the art on image-text and text-image retrieval, video question answering and open-vocabulary detection tasks, outperforming much larger and more extensively trained foundational models. It shows very competitive results on VQA and Video Captioning, especially considering its capacity. Ablations confirm the flexibility and advantages of our approach.