PyTorchKR Papers

최신 논문

총 461편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2103.10095공식 코드 · Papers with Code

On Semantic Similarity in Video Retrieval

Current video retrieval efforts all found their evaluation on an instance-based assumption, that only a single caption is relevant to a query video and vice versa. We demonstrate that this assumption results in performance comparisons often not indicative of models' retrieval capabilities. We propose a move to semantic similarity video retrieval, where (i) multiple videos/captions can be deemed equally relevant, and their relative ranking does not affect a method's reported performance and (ii) retrieved videos/captions are ranked by their similarity to a query. We propose several proxies to estimate semantic similarities in large-scale retrieval datasets, without additional annotations. Our analysis is performed on three commonly used video retrieval datasets (MSR-VTT, YouCook2 and EPIC-KITCHENS).

arXiv:2103.05457공식 코드 · Papers with Code

Rudder: A Cross Lingual Video and Text Retrieval Dataset

Video retrieval using natural language queries requires learning semantically meaningful joint embeddings between the text and the audio-visual input. Often, such joint embeddings are learnt using pairwise (or triplet) contrastive loss objectives which cannot give enough attention to 'difficult-to-retrieve' samples during training. This problem is especially pronounced in data-scarce settings where the data is relatively small (10% of the large scale MSR-VTT) to cover the rather complex audio-visual embedding space. In this context, we introduce Rudder - a multilingual video-text retrieval dataset that includes audio and textual captions in Marathi, Hindi, Tamil, Kannada, Malayalam and Telugu. Furthermore, we propose to compensate for data scarcity by using domain knowledge to augment supervision. To this end, in addition to the conventional three samples of a triplet (anchor, positive, and negative), we introduce a fourth term - a partial - to define a differential margin based partialorder loss. The partials are heuristically sampled such that they semantically lie in the overlap zone between the positives and the negatives, thereby resulting in broader embedding coverage. Our proposals consistently outperform the conventional max-margin and triplet losses and improve the state-of-the-art on MSR-VTT and DiDeMO datasets. We report benchmark results on Rudder while also observing significant gains using the proposed partial order loss, especially when the language specific retrieval models are jointly trained by availing the cross-lingual alignment across the language-specific datasets.

arXiv:2102.12443공식 코드 · Papers with Code

A Straightforward Framework For Video Retrieval Using CLIP

Video Retrieval is a challenging task where a text query is matched to a video or vice versa. Most of the existing approaches for addressing such a problem rely on annotations made by the users. Although simple, this approach is not always feasible in practice. In this work, we explore the application of the language-image model, CLIP, to obtain video representations without the need for said annotations. This model was explicitly trained to learn a common space where images and text can be compared. Using various techniques described in this document, we extended its application to videos, obtaining state-of-the-art results on the MSR-VTT and MSVD benchmarks.

arXiv:2102.11603공식 코드 · Papers with Code

SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition

Visual Place Recognition (VPR) is the task of matching current visual imagery from a camera to images stored in a reference map of the environment. While initial VPR systems used simple direct image methods or hand-crafted visual features, recent work has focused on learning more powerful visual features and further improving performance through either some form of sequential matcher / filter or a hierarchical matching process. In both cases the performance of the initial single-image based system is still far from perfect, putting significant pressure on the sequence matching or (in the case of hierarchical systems) pose refinement stages. In this paper we present a novel hybrid system that creates a high performance initial match hypothesis generator using short learnt sequential descriptors, which enable selective control sequential score aggregation using single image learnt descriptors. Sequential descriptors are generated using a temporal convolutional network dubbed SeqNet, encoding short image sequences using 1-D convolutions, which are then matched against the corresponding temporal descriptors from the reference dataset to provide an ordered list of place match hypotheses. We then perform selective sequential score aggregation using shortlisted single image learnt descriptors from a separate pipeline to produce an overall place match hypothesis. Comprehensive experiments on challenging benchmark datasets demonstrate the proposed method outperforming recent state-of-the-art methods using the same amount of sequential information. Source code and supplementary material can be found at https://github.com/oravus/seqNet.

arXiv:2102.10162

Clarification of Video Retrieval Query Results by the Automated Insertion of Supporting Shots

Computational Video Editing Systems output video generally follows a particular form, e.g. conversation or music videos, in this way they are domain specific. We describe a recent development in our video annotation and segmentation system to support general computational video editing in which we derive a single generic editing strategy from general cinema narrative principles instead of using a hierarchical film gram-mar. We demonstrate how this single principle coupled with a database of scripts derived from annotated videos leverages the existing video editing knowledge encoded within the editing of those sequences in a flexible and generic manner. We discuss the cinema theory foundations for this generic editing strategy, review the algorithms used to effect it, and goon by means of examples to show its appropriateness in an automated system.

논문 ID: 2019.29205

Multimedia Retrieval Through Unsupervised Hypergraph-Based Manifold Ranking

Accurately ranking images and multimedia objects are of paramount relevance in many retrieval and learning tasks. Manifold learning methods have been investigated for ranking mainly due to their capacity of taking into account the intrinsic global manifold structure. In this paper, a novel manifold ranking algorithm is proposed based on the hypergraphs for unsupervised multimedia retrieval tasks. Different from traditional graph-based approaches, which represent only pairwise relationships, hypergraphs are capable of modeling similarity relationships among a set of objects. The proposed approach uses the hyperedges for constructing a contextual representation of data samples and exploits the encoded information for deriving a more effective similarity function. An extensive experimental evaluation was conducted on nine public datasets including diverse retrieval scenarios and multimedia content. Experimental results demonstrate that high effectiveness gains can be obtained in comparison with the state-of-the-art methods.

arXiv:2102.07355공식 코드 · Papers with Code

Win-Fail Action Recognition

Current video/action understanding systems have demonstrated impressive performance on large recognition tasks. However, they might be limiting themselves to learning to recognize spatiotemporal patterns, rather than attempting to thoroughly understand the actions. To spur progress in the direction of a truer, deeper understanding of videos, we introduce the task of win-fail action recognition -- differentiating between successful and failed attempts at various activities. We introduce a first of its kind paired win-fail action understanding dataset with samples from the following domains: "General Stunts," "Internet Wins-Fails," "Trick Shots," and "Party Games." Unlike existing action recognition datasets, intra-class variation is high making the task challenging, yet feasible. We systematically analyze the characteristics of the win-fail task/dataset with prototypical action recognition networks and a novel video retrieval task. While current action recognition methods work well on our task/dataset, they still leave a large gap to achieve high performance. We hope to motivate more work towards the true understanding of actions/videos. Dataset will be available from https://github.com/ParitoshParmar/Win-Fail-Action-Recognition.

arXiv:2102.06183공식 코드 · Papers with Code

Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling

The canonical approach to video-and-language learning (e.g., video question answering) dictates a neural model to learn from offline-extracted dense video features from vision models and text features from language models. These feature extractors are trained independently and usually on tasks different from the target domains, rendering these fixed features sub-optimal for downstream tasks. Moreover, due to the high computational overload of dense video features, it is often difficult (or infeasible) to plug feature extractors directly into existing approaches for easy finetuning. To provide a remedy to this dilemma, we propose a generic framework ClipBERT that enables affordable end-to-end learning for video-and-language tasks, by employing sparse sampling, where only a single or a few sparsely sampled short clips from a video are used at each training step. Experiments on text-to-video retrieval and video question answering on six datasets demonstrate that ClipBERT outperforms (or is on par with) existing methods that exploit full-length videos, suggesting that end-to-end learning with just a few sparsely sampled clips is often more accurate than using densely extracted offline features from full-length videos, proving the proverbial less-is-more principle. Videos in the datasets are from considerably different domains and lengths, ranging from 3-second generic domain GIF videos to 180-second YouTube human activity videos, showing the generalization ability of our approach. Comprehensive ablation studies and thorough analyses are provided to dissect what factors lead to this success. Our code is publicly available at https://github.com/jayleicn/ClipBERT

arXiv:2101.00820

Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval

Attempt to fully discover the temporal diversity and chronological characteristics for self-supervised video representation learning, this work takes advantage of the temporal dependencies within videos and further proposes a novel self-supervised method named Temporal Contrastive Graph Learning (TCGL). In contrast to the existing methods that ignore modeling elaborate temporal dependencies, our TCGL roots in a hybrid graph contrastive learning strategy to jointly regard the inter-snippet and intra-snippet temporal dependencies as self-supervision signals for temporal representation learning. To model multi-scale temporal dependencies, our TCGL integrates the prior knowledge about the frame and snippet orders into graph structures, i.e., the intra-/inter- snippet temporal contrastive graphs. By randomly removing edges and masking nodes of the intra-snippet graphs or inter-snippet graphs, our TCGL can generate different correlated graph views. Then, specific contrastive learning modules are designed to maximize the agreement between nodes in different views. To adaptively learn the global context representation and recalibrate the channel-wise features, we introduce an adaptive video snippet order prediction module, which leverages the relational knowledge among video snippets to predict the actual snippet orders. Experimental results demonstrate the superiority of our TCGL over the state-of-the-art methods on large-scale action recognition and video retrieval benchmarks.

arXiv:1810.04401

V3C - a Research Video Collection

With the widespread use of smartphones as recording devices and the massive growth in bandwidth, the number and volume of video collections has increased significantly in the last years. This poses novel challenges to the management of these large-scale video data and especially to the analysis of and retrieval from such video collections. At the same time, existing video datasets used for research and experimentation are either not large enough to represent current collections or do not reflect the properties of video commonly found on the Internet in terms of content, length, or resolution. In this paper, we introduce the Vimeo Creative Commons Collection, in short V3C, a collection of 28'450 videos (with overall length of about 3'800 hours) published under creative commons license on Vimeo. V3C comes with a shot segmentation for each video, together with the resulting keyframes in original as well as reduced resolution and additional metadata. It is intended to be used from 2019 at the International large-scale TREC Video Retrieval Evaluation campaign (TRECVid).

arXiv:1604.07939

Large-Scale Query-by-Image Video Retrieval Using Bloom Filters

We consider the problem of using image queries to retrieve videos from a database. Our focus is on large-scale applications, where it is infeasible to index each database video frame independently. Our main contribution is a framework based on Bloom filters, which can be used to index long video segments, enabling efficient image-to-video comparisons. Using this framework, we investigate several retrieval architectures, by considering different types of aggregation and different functions to encode visual information -- these play a crucial role in achieving high performance. Extensive experiments show that the proposed technique improves mean average precision by 24% on a public dataset, while being 4X faster, compared to the previous state-of-the-art.

arXiv:1601.07754

Deep Learning Based Semantic Video Indexing and Retrieval

We share the implementation details and testing results for video retrieval system based exclusively on features extracted by convolutional neural networks. We show that deep learned features might serve as universal signature for semantic content of video useful in many search and retrieval tasks. We further show that graph-based storage structure for video index allows to efficiently retrieving the content with complicated spatial and temporal search queries.

arXiv:2011.12091공식 코드 · Papers with Code

SEA: Sentence Encoder Assembly for Video Retrieval by Textual Queries

Retrieving unlabeled videos by textual queries, known as Ad-hoc Video Search (AVS), is a core theme in multimedia data management and retrieval. The success of AVS counts on cross-modal representation learning that encodes both query sentences and videos into common spaces for semantic similarity computation. Inspired by the initial success of previously few works in combining multiple sentence encoders, this paper takes a step forward by developing a new and general method for effectively exploiting diverse sentence encoders. The novelty of the proposed method, which we term Sentence Encoder Assembly (SEA), is two-fold. First, different from prior art that use only a single common space, SEA supports text-video matching in multiple encoder-specific common spaces. Such a property prevents the matching from being dominated by a specific encoder that produces an encoding vector much longer than other encoders. Second, in order to explore complementarities among the individual common spaces, we propose multi-space multi-loss learning. As extensive experiments on four benchmarks (MSR-VTT, TRECVID AVS 2016-2019, TGIF and MSVD) show, SEA surpasses the state-of-the-art. In addition, SEA is extremely ease to implement. All this makes SEA an appealing solution for AVS and promising for continuously advancing the task by harvesting new sentence encoders.

arXiv:2011.09046

A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus

Identifying a short segment in a long video that semantically matches a text query is a challenging task that has important application potentials in language-based video search, browsing, and navigation. Typical retrieval systems respond to a query with either a whole video or a pre-defined video segment, but it is challenging to localize undefined segments in untrimmed and unsegmented videos where exhaustively searching over all possible segments is intractable. The outstanding challenge is that the representation of a video must account for different levels of granularity in the temporal domain. To tackle this problem, we propose the HierArchical Multi-Modal EncodeR (HAMMER) that encodes a video at both the coarse-grained clip level and the fine-grained frame level to extract information at different scales based on multiple subtasks, namely, video retrieval, segment temporal localization, and masked language modeling. We conduct extensive experiments to evaluate our model on moment localization in video corpus on ActivityNet Captions and TVR datasets. Our approach outperforms the previous methods as well as strong baselines, establishing new state-of-the-art for this task.

arXiv:2011.07949공식 코드 · Papers with Code

RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning

We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition. This task, however, is extremely challenging due to 1) the highly complex spatial-temporal information in videos; and 2) the lack of labeled data for training. Unlike the representation learning for static images, it is difficult to construct a suitable self-supervised task to well model both motion and appearance features. More recently, several attempts have been made to learn video representation through video playback speed prediction. However, it is non-trivial to obtain precise speed labels for the videos. More critically, the learnt models may tend to focus on motion pattern and thus may not learn appearance features well. In this paper, we observe that the relative playback speed is more consistent with motion pattern, and thus provide more effective and stable supervision for representation learning. Therefore, we propose a new way to perceive the playback speed and exploit the relative speed between two video clips as labels. In this way, we are able to well perceive speed and learn better motion features. Moreover, to ensure the learning of appearance features, we further propose an appearance-focused task, where we enforce the model to perceive the appearance difference between two video clips. We show that optimizing the two tasks jointly consistently improves the performance on two downstream tasks, namely action recognition and video retrieval. Remarkably, for action recognition on UCF101 dataset, we achieve 93.7% accuracy without the use of labeled data for pre-training, which outperforms the ImageNet supervised pre-trained model. Code and pre-trained models can be found at https://github.com/PeihaoChen/RSPNet.

arXiv:2011.02426공식 코드 · Papers with Code

Graph Based Temporal Aggregation for Video Retrieval

Large scale video retrieval is a field of study with a lot of ongoing research. Most of the work in the field is on video retrieval through text queries using techniques such as VSE++. However, there is little research done on video retrieval through image queries, and the work that has been done in this field either uses image queries from within the video dataset or iterates through videos frame by frame. These approaches are not generalized for queries from outside the dataset and do not scale well for large video datasets. To overcome these issues, we propose a new approach for video retrieval through image queries where an undirected graph is constructed from the combined set of frames from all videos to be searched. The node features of this graph are used in the task of video retrieval. Experimentation is done on the MSR-VTT dataset by using query images from outside the dataset. To evaluate this novel approach P@5, P@10 and P@20 metrics are calculated. Two different ResNet models namely, ResNet-152 and ResNet-50 are used in this study.

arXiv:2011.00597공식 코드 · Papers with Code

COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning

Many real-world video-text tasks involve different levels of granularity, such as frames and words, clip and sentences or videos and paragraphs, each with distinct semantics. In this paper, we propose a Cooperative hierarchical Transformer (COOT) to leverage this hierarchy information and model the interactions between different levels of granularity and different modalities. The method consists of three major components: an attention-aware feature aggregation layer, which leverages the local temporal context (intra-level, e.g., within a clip), a contextual transformer to learn the interactions between low-level and high-level semantics (inter-level, e.g. clip-video, sentence-paragraph), and a cross-modal cycle-consistency loss to connect video and text. The resulting method compares favorably to the state of the art on several benchmarks while having few parameters. All code is available open-source at https://github.com/gingsi/coot-videotext

arXiv:2010.15464공식 코드 · Papers with Code

Pretext-Contrastive Learning: Toward Good Practices in Self-supervised Video Representation Leaning

Recently, pretext-task based methods are proposed one after another in self-supervised video feature learning. Meanwhile, contrastive learning methods also yield good performance. Usually, new methods can beat previous ones as claimed that they could capture "better" temporal information. However, there exist setting differences among them and it is hard to conclude which is better. It would be much more convincing in comparison if these methods have reached as closer to their performance limits as possible. In this paper, we start from one pretext-task baseline, exploring how far it can go by combining it with contrastive learning, data pre-processing, and data augmentation. A proper setting has been found from extensive experiments, with which huge improvements over the baselines can be achieved, indicating a joint optimization framework can boost both pretext task and contrastive learning. We denote the joint optimization framework as Pretext-Contrastive Learning (PCL). The other two pretext task baselines are used to validate the effectiveness of PCL. And we can easily outperform current state-of-the-art methods in the same training manner, showing the effectiveness and the generality of our proposal. It is convenient to treat PCL as a standard training strategy and apply it to many other works in self-supervised video feature learning.

arXiv:2010.08737공식 코드 · Papers with Code

Audio-based Near-Duplicate Video Retrieval with Audio Similarity Learning

In this work, we address the problem of audio-based near-duplicate video retrieval. We propose the Audio Similarity Learning (AuSiL) approach that effectively captures temporal patterns of audio similarity between video pairs. For the robust similarity calculation between two videos, we first extract representative audio-based video descriptors by leveraging transfer learning based on a Convolutional Neural Network (CNN) trained on a large scale dataset of audio events, and then we calculate the similarity matrix derived from the pairwise similarity of these descriptors. The similarity matrix is subsequently fed to a CNN network that captures the temporal structures existing within its content. We train our network following a triplet generation process and optimizing the triplet loss function. To evaluate the effectiveness of the proposed approach, we have manually annotated two publicly available video datasets based on the audio duplicity between their videos. The proposed approach achieves very competitive results compared to three state-of-the-art methods. Also, unlike the competing methods, it is very robust to the retrieval of audio duplicates generated with speed transformations.

arXiv:2010.09709공식 코드 · Papers with Code

Self-supervised Co-training for Video Representation Learning

The objective of this paper is visual-only self-supervised video representation learning. We make the following contributions: (i) we investigate the benefit of adding semantic-class positives to instance-based Info Noise Contrastive Estimation (InfoNCE) training, showing that this form of supervised contrastive learning leads to a clear improvement in performance; (ii) we propose a novel self-supervised co-training scheme to improve the popular infoNCE loss, exploiting the complementary information from different views, RGB streams and optical flow, of the same data source by using one view to obtain positive class samples for the other; (iii) we thoroughly evaluate the quality of the learnt representation on two different downstream tasks: action recognition and video retrieval. In both cases, the proposed approach demonstrates state-of-the-art or comparable performance with other self-supervised approaches, whilst being significantly more efficient to train, i.e. requiring far less training data to achieve similar performance.