Untrimmed videos have interrelated events, dependencies, context, overlapping events, object-object interactions, domain specificity, and other semantics that are worth highlighting while describing a video in natural language. Owing to such a vast diversity, a single sentence can only correctly describe a portion of the video. Dense Video Captioning (DVC) aims at detecting and describing different events in a given video. The term DVC originated in the 2017 ActivityNet challenge, after which considerable effort has been made to address the challenge. Dense Video Captioning is divided into three sub-tasks: (1) Video Feature Extraction (VFE), (2) Temporal Event Localization (TEL), and (3) Dense Caption Generation (DCG). This review aims to discuss all the studies that claim to perform DVC along with its sub-tasks and summarize their results. We also discuss all the datasets that have been used for DVC. Lastly, we highlight some emerging challenges and future trends in the field.
Generative models trained on internet data have revolutionized how text, image, and video content can be created. Perhaps the next milestone for generative models is to simulate realistic experience in response to actions taken by humans, robots, and other interactive agents. Applications of a real-world simulator range from controllable content creation in games and movies, to training embodied agents purely in simulation that can be directly deployed in the real world. We explore the possibility of learning a universal simulator (UniSim) of real-world interaction through generative modeling. We first make the important observation that natural datasets available for learning a real-world simulator are often rich along different dimensions (e.g., abundant objects in image data, densely sampled actions in robotics data, and diverse movements in navigation data). With careful orchestration of diverse datasets, each providing a different aspect of the overall experience, we can simulate the visual outcome of both high-level instructions such as "open the drawer" and low-level controls from otherwise static scenes and objects. We use the simulator to train both high-level vision-language policies and low-level reinforcement learning policies, each of which can be deployed in the real world in zero shot after training purely in simulation. We also show that other types of intelligence such as video captioning models can benefit from training with simulated experience, opening up even wider applications. Video demos can be found at https://universal-simulator.github.io.
Foundational multimodal models pre-trained on large scale image-text pairs or video-text pairs or both have shown strong generalization abilities on downstream tasks. However unlike image-text models, pretraining video-text models is always not feasible due to the difficulty in collecting large-scale clean and aligned data, and exponential computational costs involved in the pretraining phase. Therefore, the pertinent question to ask is: Can image-text models be adapted to video tasks and is there any benefit to using these models over pretraining directly on videos? In this work, we focus on this question by proposing a detailed study on the generalization abilities of image-text models when evaluated on video understanding tasks in a zero-shot setting. We investigate 9 foundational image-text models on a diverse set of video tasks that include video action recognition (video AR), video retrieval (video RT), video question answering (video QA), video multiple choice (video MC) and video captioning (video CP). Our experiments show that image-text models exhibit impressive performance on video AR, video RT and video MC. Furthermore, they perform moderately on video captioning and poorly on video QA. These findings shed a light on the benefits of adapting foundational image-text models to an array of video tasks while avoiding the costly pretraining step.
Instructional videos are a common source for learning text-video or even multimodal representations by leveraging subtitles extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. However, in contrast to human-annotated captions, both speech and subtitles naturally differ from the visual content of the videos and thus provide only noisy supervision. As a result, large-scale annotation-free web video training data remains sub-optimal for training text-video models. In this work, we propose to leverage the capabilities of large language models (LLMs) to obtain high-quality video descriptions aligned with videos at scale. Specifically, we prompt an LLM to create plausible video captions based on ASR subtitles of instructional videos. To this end, we introduce a prompting method that is able to take into account a longer text of subtitles, allowing us to capture the contextual information beyond one single sentence. We further prompt the LLM to generate timestamps for each produced caption based on the timestamps of the subtitles and finally align the generated captions to the video temporally. In this way, we obtain human-style video captions at scale without human supervision. We apply our method to the subtitles of the HowTo100M dataset, creating a new large-scale dataset, HowToCaption. Our evaluation shows that the resulting captions not only significantly improve the performance over many different benchmark datasets for zero-shot text-video retrieval and video captioning, but also lead to a disentangling of textual narration from the audio, boosting the performance in text-video-audio tasks.
In the domain of video surveillance, describing the behavior of each individual within the video is becoming increasingly essential, especially in complex scenarios with multiple individuals present. This is because describing each individual's behavior provides more detailed situational analysis, enabling accurate assessment and response to potential risks, ensuring the safety and harmony of public places. Currently, video-level captioning datasets cannot provide fine-grained descriptions for each individual's specific behavior. However, mere descriptions at the video-level fail to provide an in-depth interpretation of individual behaviors, making it challenging to accurately determine the specific identity of each individual. To address this challenge, we construct a human-centric video surveillance captioning dataset, which provides detailed descriptions of the dynamic behaviors of 7,820 individuals. Specifically, we have labeled several aspects of each person, such as location, clothing, and interactions with other elements in the scene, and these people are distributed across 1,012 videos. Based on this dataset, we can link individuals to their respective behaviors, allowing for further analysis of each person's behavior in surveillance videos. Besides the dataset, we propose a novel video captioning approach that can describe individual behavior in detail on a person-level basis, achieving state-of-the-art results. To facilitate further research in this field, we intend to release our dataset and code.
Surveillance videos are an essential component of daily life with various critical applications, particularly in public security. However, current surveillance video tasks mainly focus on classifying and localizing anomalous events. Existing methods are limited to detecting and classifying the predefined events with unsatisfactory semantic understanding, although they have obtained considerable performance. To address this issue, we propose a new research direction of surveillance video-and-language understanding, and construct the first multimodal surveillance video dataset. We manually annotate the real-world surveillance dataset UCF-Crime with fine-grained event content and timing. Our newly annotated dataset, UCA (UCF-Crime Annotation), contains 23,542 sentences, with an average length of 20 words, and its annotated videos are as long as 110.7 hours. Furthermore, we benchmark SOTA models for four multimodal tasks on this newly created dataset, which serve as new baselines for surveillance video-and-language understanding. Through our experiments, we find that mainstream models used in previously publicly available datasets perform poorly on surveillance video, which demonstrates the new challenges in surveillance video-and-language understanding. To validate the effectiveness of our UCA, we conducted experiments on multimodal anomaly detection. The results demonstrate that our multimodal surveillance learning can improve the performance of conventional anomaly detection tasks. All the experiments highlight the necessity of constructing this dataset to advance surveillance AI. The link to our dataset is provided at: https://xuange923.github.io/Surveillance-Video-Understanding.
Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame sampling may ignore key information in videos and thus degrade performance. Additionally, redundant information in the sampled frames may result in low efficiency in the inference of video captioning. Addressing this, we study video captioning from a different perspective in compressed domain, which brings multi-fold advantages over the existing pipeline: 1) Compared to raw images from the decoded video, the compressed video, consisting of I-frames, motion vectors and residuals, is highly distinguishable, which allows us to leverage the entire video for learning without manual sampling through a specialized model design; 2) The captioning model is more efficient in inference as smaller and less redundant information is processed. We propose a simple yet effective end-to-end transformer in the compressed domain for video captioning that enables learning from the compressed video for captioning. We show that even with a simple design, our method can achieve state-of-the-art performance on different benchmarks while running almost 2x faster than existing approaches. Code is available at https://github.com/acherstyx/CoCap.
As the most critical components in a sentence, subject, predicate and object require special attention in the video captioning task. To implement this idea, we design a novel framework, named COllaborative three-Stream Transformers (COST), to model the three parts separately and complement each other for better representation. Specifically, COST is formed by three branches of transformers to exploit the visual-linguistic interactions of different granularities in spatial-temporal domain between videos and text, detected objects and text, and actions and text. Meanwhile, we propose a cross-granularity attention module to align the interactions modeled by the three branches of transformers, then the three branches of transformers can support each other to exploit the most discriminative semantic information of different granularities for accurate predictions of captions. The whole model is trained in an end-to-end fashion. Extensive experiments conducted on three large-scale challenging datasets, i.e., YouCookII, ActivityNet Captions and MSVD, demonstrate that the proposed method performs favorably against the state-of-the-art methods.
The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.
Visual narrating focuses on generating semantic descriptions to summarize visual content of images or videos, e.g., visual captioning and visual storytelling. The challenge mainly lies in how to design a decoder to generate accurate descriptions matching visual content. Recent advances often employ a recurrent neural network (RNN), e.g., Long-Short Term Memory (LSTM), as the decoder. However, RNN is prone to diluting long-term information, which weakens its performance of capturing long-term dependencies. Recent work has demonstrated memory network (MemNet) owns the advantage of storing long-term information. However, as the decoder, it has not been well exploited for visual narrating. The reason partially comes from the difficulty of multi-modal sequential decoding with MemNet. In this article, we devise a novel memory decoder for visual narrating. Concretely, to obtain a better multi-modal representation, we first design a new multi-modal fusion method to fully merge visual and lexical information. Then, based on the fusion result, during decoding, we construct a MemNet-based decoder consisting of multiple memory layers. Particularly, in each layer, we employ a memory set to store previous decoding information and utilize an attention mechanism to adaptively select the information related to the current output. Meanwhile, we also employ a memory set to store the decoding output of each memory layer at the current time step and still utilize an attention mechanism to select the related information. Thus, this decoder alleviates dilution of long-term information. Meanwhile, the hierarchical architecture leverages the latent information of each layer, which is helpful for generating accurate descriptions. Experimental results on two tasks of visual narrating, i.e., video captioning and visual storytelling, show that our decoder could obtain superior results and outperform the performance of conventional RNN-based decoder.
Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is time-consuming and expensive for many scenarios and languages. Therefore, sufficient labeled pairs are usually not available. To deal with the label shortage problem, we present a simple yet effective zero-shot approach MultiCapCLIP that can generate visual captions for different scenarios and languages without any labeled vision-caption pairs of downstream datasets. In the training stage, MultiCapCLIP only requires text data for input. Then it conducts two main steps: 1) retrieving concept prompts that preserve the corresponding domain knowledge of new scenarios; 2) auto-encoding the prompts to learn writing styles to output captions in a desired language. In the testing stage, MultiCapCLIP instead takes visual data as input directly to retrieve the concept prompts to generate the final visual descriptions. The extensive experiments on image and video captioning across four benchmarks and four languages (i.e., English, Chinese, German, and French) confirm the effectiveness of our approach. Compared with state-of-the-art zero-shot and weakly-supervised methods, our method achieves 4.8% and 21.5% absolute improvements in terms of BLEU@4 and CIDEr metrics. Our code is available at https://github.com/yangbang18/MultiCapCLIP.
As the model size of pre-trained language models (PLMs) grows rapidly, full fine-tuning becomes prohibitively expensive for model training and storage. In vision-and-language (VL), parameter-efficient tuning (PET) techniques are proposed to integrate modular modifications (e.g., Adapter and LoRA) into encoder-decoder PLMs. By tuning a small set of trainable parameters, these techniques perform on par with full fine-tuning. However, excessive modular modifications and neglecting the functionality gap between the encoders and decoders can lead to performance degradation, while existing PET techniques (e.g., VL-Adapter) overlook these critical issues. In this paper, we propose a Vision-and-Language Parameter-Efficient Tuning (VL-PET) framework to impose effective control over modular modifications via a novel granularity-controlled mechanism. Considering different granularity-controlled matrices generated by this mechanism, a variety of model-agnostic VL-PET modules can be instantiated from our framework for better efficiency and effectiveness trade-offs. We further propose lightweight PET module designs to enhance VL alignment and modeling for the encoders and maintain text generation for the decoders. Extensive experiments conducted on four image-text tasks and four video-text tasks demonstrate the efficiency, effectiveness and transferability of our VL-PET framework. In particular, our VL-PET-large with lightweight PET module designs significantly outperforms VL-Adapter by 2.92% (3.41%) and LoRA by 3.37% (7.03%) with BART-base (T5-base) on image-text tasks. Furthermore, we validate the enhanced effect of employing our VL-PET designs on existing PET techniques, enabling them to achieve significant performance improvements. Our code is available at https://github.com/HenryHZY/VL-PET.
In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively capture the rich semantics inside the video using the image encoder of CLIP. To tackle this, state-of-the-art methods adopt complex cross-modal modeling techniques to fuse the text information into video frame representations, which, however, incurs severe efficiency issues in large-scale retrieval systems as the video representations must be recomputed online for every text query. In this paper, we discard this problematic cross-modal fusion process and aim to learn semantically-enhanced representations purely from the video, so that the video representations can be computed offline and reused for different texts. Concretely, we first introduce a spatial-temporal "Prompt Cube" into the CLIP image encoder and iteratively switch it within the encoder layers to efficiently incorporate the global video semantics into frame representations. We then propose to apply an auxiliary video captioning objective to train the frame representations, which facilitates the learning of detailed video semantics by providing fine-grained guidance in the semantic space. With a naive temporal fusion strategy (i.e., mean-pooling) on the enhanced frame representations, we obtain state-of-the-art performances on three benchmark datasets, i.e., MSR-VTT, MSVD, and LSMDC.
The application of video captioning models aims at translating the content of videos by using accurate natural language. Due to the complex nature inbetween object interaction in the video, the comprehensive understanding of spatio-temporal relations of objects remains a challenging task. Existing methods often fail in generating sufficient feature representations of video content. In this paper, we propose a video captioning model based on dual graphs and gated fusion: we adapt two types of graphs to generate feature representations of video content and utilize gated fusion to further understand these different levels of information. Using a dual-graphs model to generate appearance features and motion features respectively can utilize the content correlation in frames to generate various features from multiple perspectives. Among them, dual-graphs reasoning can enhance the content correlation in frame sequences to generate advanced semantic features; The gated fusion, on the other hand, aggregates the information in multiple feature representations for comprehensive video content understanding. The experiments conducted on worldly used datasets MSVD and MSR-VTT demonstrate state-of-the-art performance of our proposed approach.
This paper presents OmniDataComposer, an innovative approach for multimodal data fusion and unlimited data generation with an intent to refine and uncomplicate interplay among diverse data modalities. Coming to the core breakthrough, it introduces a cohesive data structure proficient in processing and merging multimodal data inputs, which include video, audio, and text. Our crafted algorithm leverages advancements across multiple operations such as video/image caption extraction, dense caption extraction, Automatic Speech Recognition (ASR), Optical Character Recognition (OCR), Recognize Anything Model(RAM), and object tracking. OmniDataComposer is capable of identifying over 6400 categories of objects, substantially broadening the spectrum of visual information. It amalgamates these diverse modalities, promoting reciprocal enhancement among modalities and facilitating cross-modal data correction. \textbf{The final output metamorphoses each video input into an elaborate sequential document}, virtually transmuting videos into thorough narratives, making them easier to be processed by large language models. Future prospects include optimizing datasets for each modality to encourage unlimited data generation. This robust base will offer priceless insights to models like ChatGPT, enabling them to create higher quality datasets for video captioning and easing question-answering tasks based on video content. OmniDataComposer inaugurates a new stage in multimodal learning, imparting enormous potential for augmenting AI's understanding and generation of complex, real-world data.
Recent advancements in surgical computer vision applications have been driven by vision-only models, which do not explicitly integrate the rich semantics of language into their design. These methods rely on manually annotated surgical videos to predict a fixed set of object categories, limiting their generalizability to unseen surgical procedures and downstream tasks. In this work, we put forward the idea that the surgical video lectures available through open surgical e-learning platforms can provide effective vision and language supervisory signals for multi-modal representation learning without relying on manual annotations. We address the surgery-specific linguistic challenges present in surgical video lectures by employing multiple complementary automatic speech recognition systems to generate text transcriptions. We then present a novel method, SurgVLP - Surgical Vision Language Pre-training, for multi-modal representation learning. Extensive experiments across diverse surgical procedures and tasks demonstrate that the multi-modal representations learned by SurgVLP exhibit strong transferability and adaptability in surgical video analysis. Furthermore, our zero-shot evaluations highlight SurgVLP's potential as a general-purpose foundation model for surgical workflow analysis, reducing the reliance on extensive manual annotations for downstream tasks, and facilitating adaptation methods such as few-shot learning to build a scalable and data-efficient solution for various downstream surgical applications. The [training code](https://github.com/CAMMA-public/SurgVLP) and [weights](https://github.com/CAMMA-public/PeskaVLP) are public.
Dense video captioning, a task of localizing meaningful moments and generating relevant captions for videos, often requires a large, expensive corpus of annotated video segments paired with text. In an effort to minimize the annotation cost, we propose ZeroTA, a novel method for dense video captioning in a zero-shot manner. Our method does not require any videos or annotations for training; instead, it localizes and describes events within each input video at test time by optimizing solely on the input. This is accomplished by introducing a soft moment mask that represents a temporal segment in the video and jointly optimizing it with the prefix parameters of a language model. This joint optimization aligns a frozen language generation model (i.e., GPT-2) with a frozen vision-language contrastive model (i.e., CLIP) by maximizing the matching score between the generated text and a moment within the video. We also introduce a pairwise temporal IoU loss to let a set of soft moment masks capture multiple distinct events within the video. Our method effectively discovers diverse significant events within the video, with the resulting captions appropriately describing these events. The empirical results demonstrate that ZeroTA surpasses zero-shot baselines and even outperforms the state-of-the-art few-shot method on the widely-used benchmark ActivityNet Captions. Moreover, our method shows greater robustness compared to supervised methods when evaluated in out-of-domain scenarios. This research provides insight into the potential of aligning widely-used models, such as language generation models and vision-language models, to unlock a new capability: understanding temporal aspects of videos.
We present CausalVLR (Causal Visual-Linguistic Reasoning), an open-source toolbox containing a rich set of state-of-the-art causal relation discovery and causal inference methods for various visual-linguistic reasoning tasks, such as VQA, image/video captioning, medical report generation, model generalization and robustness, etc. These methods have been included in the toolbox with PyTorch implementations under NVIDIA computing system. It not only includes training and inference codes, but also provides model weights. We believe this toolbox is by far the most complete visual-linguitic causal reasoning toolbox. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to re-implement existing methods and develop their own new causal reasoning methods. Code and models are available at https://github.com/HCPLab-SYSU/CausalVLR. The project is under active development by HCP-Lab's contributors and we will keep this document updated.
To realize human-robot collaboration, robots need to execute actions for new tasks according to human instructions given finite prior knowledge. Human experts can share their knowledge of how to perform a task with a robot through multi-modal instructions in their demonstrations, showing a sequence of short-horizon steps to achieve a long-horizon goal. This paper introduces a method for robot action sequence generation from instruction videos using (1) an audio-visual Transformer that converts audio-visual features and instruction speech to a sequence of robot actions called dynamic movement primitives (DMPs) and (2) style-transfer-based training that employs multi-task learning with video captioning and weakly-supervised learning with a semantic classifier to exploit unpaired video-action data. We built a system that accomplishes various cooking actions, where an arm robot executes a DMP sequence acquired from a cooking video using the audio-visual Transformer. Experiments with Epic-Kitchen-100, YouCookII, QuerYD, and in-house instruction video datasets show that the proposed method improves the quality of DMP sequences by 2.3 times the METEOR score obtained with a baseline video-to-action Transformer. The model achieved 32% of the task success rate with the task knowledge of the object.
Recent focus in video captioning has been on designing architectures that can consume both video and text modalities, and using large-scale video datasets with text transcripts for pre-training, such as HowTo100M. Though these approaches have achieved significant improvement, the audio modality is often ignored in video captioning. In this work, we present an audio-visual framework, which aims to fully exploit the potential of the audio modality for captioning. Instead of relying on text transcripts extracted via automatic speech recognition (ASR), we argue that learning with raw audio signals can be more beneficial, as audio has additional information including acoustic events, speaker identity, etc. Our contributions are twofold. First, we observed that the model overspecializes to the audio modality when pre-training with both video and audio modality, since the ground truth (i.e., text transcripts) can be solely predicted using audio. We proposed a Modality Balanced Pre-training (MBP) loss to mitigate this issue and significantly improve the performance on downstream tasks. Second, we slice and dice different design choices of the cross-modal module, which may become an information bottleneck and generate inferior results. We proposed new local-global fusion mechanisms to improve information exchange across audio and video. We demonstrate significant improvements by leveraging the audio modality on four datasets, and even outperform the state of the art on some metrics without relying on the text modality as the input.