PyTorchKR Papers

최신 논문

총 440편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2207.11838

SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions

Detecting suspicious activities in surveillance videos is a longstanding problem in real-time surveillance that leads to difficulties in detecting crimes. Hence, we propose a novel approach for detecting and summarizing suspicious activities in surveillance videos. We have also created ground truth summaries for the UCF-Crime video dataset. We modify a pre-existing approach for this task by leveraging the Human-Object Interaction (HOI) model for the Visual features in the Bi-Modal Transformer. Further, we validate our approach against the existing state-of-the-art algorithms for the Dense Video Captioning task for the ActivityNet Captions dataset. We observe that this formulation for Dense Captioning performs significantly better than other discussed BMT-based approaches for BLEU@1, BLEU@2, BLEU@3, BLEU@4, and METEOR. We further perform a comparative analysis of the dataset and the model to report the findings based on different NMS thresholds (searched using Genetic Algorithms). Here, our formulation outperforms all the models for BLEU@1, BLEU@2, BLEU@3, and most models for BLEU@4 and METEOR falling short of only ADV-INF Global by 25% and 0.5%, respectively.

arXiv:2207.11100공식 코드 · Papers with Code

Zero-Shot Video Captioning with Evolving Pseudo-Tokens

We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model. The matching score is used to steer the language model toward generating a sentence that has a high average matching score to a subset of the video frames. Unlike zero-shot image captioning methods, our work considers the entire sentence at once. This is achieved by optimizing, during the generation process, part of the prompt from scratch, by modifying the representation of all other tokens in the prompt, and by repeating the process iteratively, gradually improving the specificity and comprehensiveness of the generated sentence. Our experiments show that the generated captions are coherent and display a broad range of real-world knowledge. Our code is available at: https://github.com/YoadTew/zero-shot-video-to-text

arXiv:2207.08625공식 코드 · Papers with Code

Unifying Event Detection and Captioning as Sequence Generation via Pre-Training

Dense video captioning aims to generate corresponding text descriptions for a series of events in the untrimmed video, which can be divided into two sub-tasks, event detection and event captioning. Unlike previous works that tackle the two sub-tasks separately, recent works have focused on enhancing the inter-task association between the two sub-tasks. However, designing inter-task interactions for event detection and captioning is not trivial due to the large differences in their task specific solutions. Besides, previous event detection methods normally ignore temporal dependencies between events, leading to event redundancy or inconsistency problems. To tackle above the two defects, in this paper, we define event detection as a sequence generation task and propose a unified pre-training and fine-tuning framework to naturally enhance the inter-task association between event detection and captioning. Since the model predicts each event with previous events as context, the inter-dependency between events is fully exploited and thus our model can detect more diverse and consistent events in the video. Experiments on the ActivityNet dataset show that our model outperforms the state-of-the-art methods, and can be further boosted when pre-trained on extra large-scale video-text data. Code is available at \url{https://github.com/QiQAng/UEDVC}.

arXiv:2207.03038공식 코드 · Papers with Code

Dual-Stream Transformer for Generic Event Boundary Captioning

This paper describes our champion solution for the CVPR2022 Generic Event Boundary Captioning (GEBC) competition. GEBC requires the captioning model to have a comprehension of instantaneous status changes around the given video boundary, which makes it much more challenging than conventional video captioning task. In this paper, a Dual-Stream Transformer with improvements on both video content encoding and captions generation is proposed: (1) We utilize three pre-trained models to extract the video features from different granularities. Moreover, we exploit the types of boundary as hints to help the model generate captions. (2) We particularly design an model, termed as Dual-Stream Transformer, to learn discriminative representations for boundary captioning. (3) Towards generating content-relevant and human-like captions, we improve the description quality by designing a word-level ensemble strategy. The promising results on the GEBC test split demonstrate the efficacy of our proposed model.

arXiv:2207.02583

PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning

The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video. Semantic information plays an important role for both localization and description of DVC. We present a semantic-assisted dense video captioning model based on the encoding-decoding framework. In the encoding stage, we design a concept detector to extract semantic information, which is then fused with multi-modal visual features to sufficiently represent the input video. In the decoding stage, we design a classification head, paralleled with the localization and captioning heads, to provide semantic supervision. Our method achieves significant improvements on the YouMakeup dataset under DVC evaluation metrics and achieves high performance in the Makeup Dense Video Captioning (MDVC) task of PIC 4th Challenge.

arXiv:2207.00113공식 코드 · Papers with Code

Rethinking Surgical Captioning: End-to-End Window-Based MLP Transformer Using Patches

Surgical captioning plays an important role in surgical instruction prediction and report generation. However, the majority of captioning models still rely on the heavy computational object detector or feature extractor to extract regional features. In addition, the detection model requires additional bounding box annotation which is costly and needs skilled annotators. These lead to inference delay and limit the captioning model to deploy in real-time robotic surgery. For this purpose, we design an end-to-end detector and feature extractor-free captioning model by utilizing the patch-based shifted window technique. We propose Shifted Window-Based Multi-Layer Perceptrons Transformer Captioning model (SwinMLP-TranCAP) with faster inference speed and less computation. SwinMLP-TranCAP replaces the multi-head attention module with window-based multi-head MLP. Such deployments primarily focus on image understanding tasks, but very few works investigate the caption generation task. SwinMLP-TranCAP is also extended into a video version for video captioning tasks using 3D patches and windows. Compared with previous detector-based or feature extractor-based models, our models greatly simplify the architecture design while maintaining performance on two surgical datasets. The code is publicly available at https://github.com/XuMengyaAmy/SwinMLP_TranCAP.

arXiv:2206.12972공식 코드 · Papers with Code

VLCap: Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning

In this paper, we leverage the human perceiving process, that involves vision and language interaction, to generate a coherent paragraph description of untrimmed videos. We propose vision-language (VL) features consisting of two modalities, i.e., (i) vision modality to capture global visual content of the entire scene and (ii) language modality to extract scene elements description of both human and non-human objects (e.g. animals, vehicles, etc), visual and non-visual elements (e.g. relations, activities, etc). Furthermore, we propose to train our proposed VLCap under a contrastive learning VL loss. The experiments and ablation studies on ActivityNet Captions and YouCookII datasets show that our VLCap outperforms existing SOTA methods on both accuracy and diversity metrics.

arXiv:2206.07160공식 코드 · Papers with Code

LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling

Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still require task-specific designs in model architecture and training objectives for each task. In this work, we explore a unified VidL framework LAVENDER, where Masked Language Modeling (MLM) is used as the common interface for all pre-training and downstream tasks. Such unification leads to a simplified model architecture, where only a lightweight MLM head, instead of a decoder with much more parameters, is needed on top of the multimodal encoder. Surprisingly, experimental results show that this unified framework achieves competitive performance on 14 VidL benchmarks, covering video question answering, text-to-video retrieval and video captioning. Extensive analyses further demonstrate the advantage of LAVENDER over existing VidL methods in: (i) supporting all downstream tasks with just a single set of parameter values when multi-task finetuned; (ii) few-shot generalization on various downstream tasks; and (iii) enabling zero-shot evaluation on video question answering tasks. Code is available at https://github.com/microsoft/LAVENDER.

arXiv:2206.04674공식 코드 · Papers with Code

Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs

To build an artificial neural network like the biological intelligence system, recent works have unified numerous tasks into a generalist model, which can process various tasks with shared parameters and do not have any task-specific modules. While generalist models achieve promising results on various benchmarks, they have performance degradation on some tasks compared with task-specialized models. In this work, we find that interference among different tasks and modalities is the main factor to this phenomenon. To mitigate such interference, we introduce the Conditional Mixture-of-Experts (Conditional MoEs) to generalist models. Routing strategies under different levels of conditions are proposed to take both the training/inference cost and generalization ability into account. By incorporating the proposed Conditional MoEs, the recently proposed generalist model Uni-Perceiver can effectively mitigate the interference across tasks and modalities, and achieves state-of-the-art results on a series of downstream tasks via prompt tuning on 1% of downstream data. Moreover, the introduction of Conditional MoEs still holds the generalization ability of generalist models to conduct zero-shot inference on new tasks, e.g., video-text retrieval and video caption. Code and pre-trained generalist models shall be released.

arXiv:2205.14100공식 코드 · Papers with Code

GIT: A Generative Image-to-text Transformer for Vision and Language

In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between pre-training and fine-tuning, existing work typically contains complex structures (uni/multi-modal encoder/decoder) and depends on external modules such as object detectors/taggers and optical character recognition (OCR). In GIT, we simplify the architecture as one image encoder and one text decoder under a single language modeling task. We also scale up the pre-training data and the model size to boost the model performance. Without bells and whistles, our GIT establishes new state of the arts on 12 challenging benchmarks with a large margin. For instance, our model surpasses the human performance for the first time on TextCaps (138.2 vs. 125.5 in CIDEr). Furthermore, we present a new scheme of generation-based image classification and scene text recognition, achieving decent performance on standard benchmarks. Codes are released at \url{https://github.com/microsoft/GenerativeImage2Text}.

arXiv:2205.10706공식 코드 · Papers with Code

GL-RG: Global-Local Representation Granularity for Video Captioning

Video captioning is a challenging task as it needs to accurately transform visual understanding into natural language description. To date, state-of-the-art methods inadequately model global-local representation across video frames for caption generation, leaving plenty of room for improvement. In this work, we approach the video captioning task from a new perspective and propose a GL-RG framework for video captioning, namely a \textbf{G}lobal-\textbf{L}ocal \textbf{R}epresentation \textbf{G}ranularity. Our GL-RG demonstrates three advantages over the prior efforts: 1) we explicitly exploit extensive visual representations from different video ranges to improve linguistic expression; 2) we devise a novel global-local encoder to produce rich semantic vocabulary to obtain a descriptive granularity of video contents across frames; 3) we develop an incremental training strategy which organizes model learning in an incremental fashion to incur an optimal captioning behavior. Experimental results on the challenging MSR-VTT and MSVD datasets show that our DL-RG outperforms recent state-of-the-art methods by a significant margin. Code is available at \url{https://github.com/ylqi/GL-RG}.

arXiv:2205.10747공식 코드 · Papers with Code

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

The goal of this work is to build flexible video-language models that can generalize to various video-to-text tasks from few examples, such as domain-specific captioning, question answering, and future event prediction. Existing few-shot video-language learners focus exclusively on the encoder, resulting in the absence of a video-to-text decoder to handle generative tasks. Video captioners have been pretrained on large-scale video-language datasets, but they rely heavily on finetuning and lack the ability to generate text for unseen tasks in a few-shot setting. We propose VidIL, a few-shot Video-language Learner via Image and Language models, which demonstrates strong performance on few-shot video-to-text tasks without the necessity of pretraining or finetuning on any video datasets. We use the image-language models to translate the video content into frame captions, object, attribute, and event phrases, and compose them into a temporal structure template. We then instruct a language model, with a prompt containing a few in-context examples, to generate a target output from the composed content. The flexibility of prompting allows the model to capture any form of text input, such as automatic speech recognition (ASR) transcripts. Our experiments demonstrate the power of language models in understanding videos on a wide variety of video-language tasks, including video captioning, video question answering, video caption retrieval, and video future event prediction. Especially, on video future event prediction, our few-shot model significantly outperforms state-of-the-art supervised models trained on large-scale video datasets. Code and resources are publicly available for research purposes at https://github.com/MikeWangWZHL/VidIL .

arXiv:2205.09307공식 코드 · Papers with Code

Support-set based Multi-modal Representation Enhancement for Video Captioning

Video captioning is a challenging task that necessitates a thorough comprehension of visual scenes. Existing methods follow a typical one-to-one mapping, which concentrates on a limited sample space while ignoring the intrinsic semantic associations between samples, resulting in rigid and uninformative expressions. To address this issue, we propose a novel and flexible framework, namely Support-set based Multi-modal Representation Enhancement (SMRE) model, to mine rich information in a semantic subspace shared between samples. Specifically, we propose a Support-set Construction (SC) module to construct a support-set to learn underlying connections between samples and obtain semantic-related visual elements. During this process, we design a Semantic Space Transformation (SST) module to constrain relative distance and administrate multi-modal interactions in a self-supervised way. Extensive experiments on MSVD and MSR-VTT datasets demonstrate that our SMRE achieves state-of-the-art performance.

arXiv:2205.03534

Attract me to Buy: Advertisement Copywriting Generation with Multimodal Multi-structured Information

Recently, online shopping has gradually become a common way of shopping for people all over the world. Wonderful merchandise advertisements often attract more people to buy. These advertisements properly integrate multimodal multi-structured information of commodities, such as visual spatial information and fine-grained structure information. However, traditional multimodal text generation focuses on the conventional description of what existed and happened, which does not match the requirement of advertisement copywriting in the real world. Because advertisement copywriting has a vivid language style and higher requirements of faithfulness. Unfortunately, there is a lack of reusable evaluation frameworks and a scarcity of datasets. Therefore, we present a dataset, E-MMAD (e-commercial multimodal multi-structured advertisement copywriting), which requires, and supports much more detailed information in text generation. Noticeably, it is one of the largest video captioning datasets in this field. Accordingly, we propose a baseline method and faithfulness evaluation metric on the strength of structured information reasoning to solve the demand in reality on this dataset. It surpasses the previous methods by a large margin on all metrics. The dataset and method are coming soon on \url{https://e-mmad.github.io/e-mmad.net/index.html}.

arXiv:2205.03039

Dual-Level Decoupled Transformer for Video Captioning

Video captioning aims to understand the spatio-temporal semantic concept of the video and generate descriptive sentences. The de-facto approach to this task dictates a text generator to learn from \textit{offline-extracted} motion or appearance features from \textit{pre-trained} vision models. However, these methods may suffer from the so-called \textbf{\textit{"couple"}} drawbacks on both \textit{video spatio-temporal representation} and \textit{sentence generation}. For the former, \textbf{\textit{"couple"}} means learning spatio-temporal representation in a single model(3DCNN), resulting the problems named \emph{disconnection in task/pre-train domain} and \emph{hard for end-to-end training}. As for the latter, \textbf{\textit{"couple"}} means treating the generation of visual semantic and syntax-related words equally. To this end, we present $\mathcal{D}^{2}$ - a dual-level decoupled transformer pipeline to solve the above drawbacks: \emph{(i)} for video spatio-temporal representation, we decouple the process of it into "first-spatial-then-temporal" paradigm, releasing the potential of using dedicated model(\textit{e.g.} image-text pre-training) to connect the pre-training and downstream tasks, and makes the entire model end-to-end trainable. \emph{(ii)} for sentence generation, we propose \emph{Syntax-Aware Decoder} to dynamically measure the contribution of visual semantic and syntax-related words. Extensive experiments on three widely-used benchmarks (MSVD, MSR-VTT and VATEX) have shown great potential of the proposed $\mathcal{D}^{2}$ and surpassed the previous methods by a large margin in the task of video captioning.

arXiv:2204.13548공식 코드 · Papers with Code

Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos

In videos that contain actions performed unintentionally, agents do not achieve their desired goals. In such videos, it is challenging for computer vision systems to understand high-level concepts such as goal-directed behavior, an ability present in humans from a very early age. Inculcating this ability in artificially intelligent agents would make them better social learners by allowing them to evaluate human action under a teleological lens. To validate the ability of deep learning models to perform this task, we curate the W-Oops dataset, built upon the Oops dataset [15]. W-Oops consists of 2,100 unintentional human action videos, with 44 goal-directed and 30 unintentional video-level activity labels collected through human annotations. Due to the expensive segment annotation procedure, we propose a weakly supervised algorithm for localizing the goal-directed as well as unintentional temporal regions in the video leveraging solely video-level labels. In particular, we employ an attention mechanism-based strategy that predicts the temporal regions which contribute the most to a classification task. Meanwhile, our designed overlap regularization allows the model to focus on distinct portions of the video for inferring the goal-directed and unintentional activity while guaranteeing their temporal ordering. Extensive quantitative experiments verify the validity of our localization method. We further conduct a video captioning experiment which demonstrates that the proposed localization module does indeed assist teleological action understanding.

arXiv:2204.08121

End-to-end Dense Video Captioning as Sequence Generation

Dense video captioning aims to identify the events of interest in an input video, and generate descriptive captions for each event. Previous approaches usually follow a two-stage generative process, which first proposes a segment for each event, then renders a caption for each identified segment. Recent advances in large-scale sequence generation pretraining have seen great success in unifying task formulation for a great variety of tasks, but so far, more complex tasks such as dense video captioning are not able to fully utilize this powerful paradigm. In this work, we show how to model the two subtasks of dense video captioning jointly as one sequence generation task, and simultaneously predict the events and the corresponding descriptions. Experiments on YouCook2 and ViTT show encouraging results and indicate the feasibility of training complex tasks such as end-to-end dense video captioning integrated into large-scale pretrained models.

arXiv:2204.08058공식 코드 · Papers with Code

MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration

Multimodal video-audio-text understanding and generation can benefit from datasets that are narrow but rich. The narrowness allows bite-sized challenges that the research community can make progress on. The richness ensures we are making progress along the core challenges. To this end, we present a large-scale video-audio-text dataset MUGEN, collected using the open-sourced platform game CoinRun [11]. We made substantial modifications to make the game richer by introducing audio and enabling new interactions. We trained RL agents with different objectives to navigate the game and interact with 13 objects and characters. This allows us to automatically extract a large collection of diverse videos and associated audio. We sample 375K video clips (3.2s each) and collect text descriptions from human annotators. Each video has additional annotations that are extracted automatically from the game engine, such as accurate semantic maps for each frame and templated textual descriptions. Altogether, MUGEN can help progress research in many tasks in multimodal understanding and generation. We benchmark representative approaches on tasks involving video-audio-text retrieval and generation. Our dataset and code are released at: https://mugen-org.github.io/.

arXiv:2204.07449

Semantic-Aware Pretraining for Dense Video Captioning

This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021. We present a semantic-aware pretraining method for dense video captioning, which empowers the learned features to recognize high-level semantic concepts. Diverse video features of different modalities are fed into an event captioning module to generate accurate and meaningful sentences. Our final ensemble model achieves a 10.00 METEOR score on the test set.

arXiv:2204.05976

Video Captioning: a comparative review of where we are and which could be the route

Video captioning is the process of describing the content of a sequence of images capturing its semantic relationships and meanings. Dealing with this task with a single image is arduous, not to mention how difficult it is for a video (or images sequence). The amount and relevance of the applications of video captioning are vast, mainly to deal with a significant amount of video recordings in video surveillance, or assisting people visually impaired, to mention a few. To analyze where the efforts of our community to solve the video captioning task are, as well as what route could be better to follow, this manuscript presents an extensive review of more than 105 papers for the period of 2016 to 2021. As a result, the most-used datasets and metrics are identified. Also, the main approaches used and the best ones. We compute a set of rankings based on several performance metrics to obtain, according to its performance, the best method with the best result on the video captioning task. Finally, some insights are concluded about which could be the next steps or opportunity areas to improve dealing with this complex task.