اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning
110
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The natural association between visual observations and their corresponding sound provides powerful self-supervisory signals for learning video representations, which makes the ever-growing amount of online videos an attractive source of training data. However, large portions of online videos contain irrelevant audio-visual signals because of edited/overdubbed audio, and models trained on such uncurated videos have shown to learn suboptimal representations. Therefore, existing approaches rely almost exclusively on datasets with predetermined taxonomies of semantic concepts, where there is a high chance of audio-visual correspondence. Unfortunately, constructing such datasets require labor intensive manual annotation and/or verification, which severely limits the utility of online videos for large-scale learning. In this work, we present an automatic dataset curation approach based on subset optimization where the objective is to maximize the mutual information between audio and visual channels in videos. We demonstrate that our approach finds videos with high audio-visual correspondence and show that self-supervised models trained on our data achieve competitive performances compared to models trained on existing manually curated datasets. The most significant benefit of our approach is scalability: We release ACAV100M that contains 100 million videos with high audio-visual correspondence, ideal for self-supervised video representation learning.
قيم البحث
اقرأ أيضاً
We describe a system for large-scale audiovisual translation and dubbing, which translates videos from one language to another. The source languages speech content is transcribed to text, translated, and automatically synthesized into target language
speech using the original speakers voice. The visual content is translated by synthesizing lip movements for the speaker to match the translated audio, creating a seamless audiovisual experience in the target language. The audio and visual translation subsystems each contain a large-scale generic synthesis model trained on thousands of hours of data in the corresponding domain. These generic models are fine-tuned to a specific speaker before translation, either using an auxiliary corpus of data from the target speaker, or using the video to be translated itself as the input to the fine-tuning process. This report gives an architectural overview of the full system, as well as an in-depth discussion of the video dubbing component. The role of the audio and text components in relation to the full system is outlined, but their design is not discussed in detail. Translated and dubbed demo videos generated using our system can be viewed at https://www.youtube.com/playlist?list=PLSi232j2ZA6_1Exhof5vndzyfbxAhhEs5
We report on CMU Informedia Labs system used in Googles YouTube 8 Million Video Understanding Challenge. In this multi-label video classification task, our pipeline achieved 84.675% and 84.662% GAP on our evaluation split and the official test set. W
e attribute the good performance to three components: 1) Refined video representation learning with residual links and hypercolumns 2) Latent concept mining which captures interactions among concepts. 3) Learning with temporal segments and weighted multi-model ensemble. We conduct experiments to validate and analyze the contribution of our models. We also share some unsuccessful trials leveraging conventional approaches such as recurrent neural networks for video representation learning for this large-scale video dataset. All the codes to reproduce our results are publicly available at https://github.com/Martini09/informedia-yt8m-release.
Our objective is to transform a video into a set of discrete audio-visual objects using self-supervised learning. To this end, we introduce a model that uses attention to localize and group sound sources, and optical flow to aggregate information ove
r time. We demonstrate the effectiveness of the audio-visual object embeddings that our model learns by using them for four downstream speech-oriented tasks: (a) multi-speaker sound source separation, (b) localizing and tracking speakers, (c) correcting misaligned audio-visual data, and (d) active speaker detection. Using our representation, these tasks can be solved entirely by training on unlabeled video, without the aid of object detectors. We also demonstrate the generality of our method by applying it to non-human speakers, including cartoons and puppets.Our model significantly outperforms other self-supervised approaches, and obtains performance competitive with methods that use supervised face detection.
When people observe events, they are able to abstract key information and build concise summaries of what is happening. These summaries include contextual and semantic information describing the important high-level details (what, where, who and how)
of the observed event and exclude background information that is deemed unimportant to the observer. With this in mind, the descriptions people generate for videos of different dynamic events can greatly improve our understanding of the key information of interest in each video. These descriptions can be captured in captions that provide expanded attributes for video labeling (e.g. actions/objects/scenes/sentiment/etc.) while allowing us to gain new insight into what people find important or necessary to summarize specific events. Existing caption datasets for video understanding are either small in scale or restricted to a specific domain. To address this, we present the Spoken Moments (S-MiT) dataset of 500k spoken captions each attributed to a unique short video depicting a broad range of different events. We collect our descriptions using audio recordings to ensure that they remain as natural and concise as possible while allowing us to scale the size of a large classification dataset. In order to utilize our proposed dataset, we present a novel Adaptive Mean Margin (AMM) approach to contrastive learning and evaluate our models on video/caption retrieval on multiple datasets. We show that our AMM approach consistently improves our results and that models trained on our Spoken Moments dataset generalize better than those trained on other video-caption datasets.
Analysts commonly investigate the data distributions derived from statistical aggregations of data that are represented by charts, such as histograms and binned scatterplots, to visualize and analyze a large-scale dataset. Aggregate queries are impli
citly executed through such a process. Datasets are constantly extremely large; thus, the response time should be accelerated by calculating predefined data cubes. However, the queries are limited to the predefined binning schema of preprocessed data cubes. Such limitation hinders analysts flexible adjustment of visual specifications to investigate the implicit patterns in the data effectively. Particularly, RSATree enables arbitrary queries and flexible binning strategies by leveraging three schemes, namely, an R-tree-based space partitioning scheme to catch the data distribution, a locality-sensitive hashing technique to achieve locality-preserving random access to data items, and a summed area table scheme to support interactive query of aggregated values with a linear computational complexity. This study presents and implements a web-based visual query system that supports visual specification, query, and exploration of large-scale tabular data with user-adjustable granularities. We demonstrate the efficiency and utility of our approach by performing various experiments on real-world datasets and analyzing time and space complexity.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
