Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels in an end-to-end fashion. However, these methods operate at frame-level directly and thus overlook the spatio-temporal structure of objects in video, which yet has a strong synergy with nouns in textual descriptions. In this work, we propose a simple yet effective module for video-text representation learning, namely RegionLearner, which can take into account the structure of objects during pre-training on large-scale video-text pairs. Given a video, our module (1) first quantizes visual features into semantic clusters, then (2) generates learnable masks and uses them to aggregate the features belonging to the same semantic region, and finally (3) models the interactions between different aggregated regions. In contrast to using off-the-shelf object detectors, our proposed module does not require explicit supervision and is much more computationally efficient. We pre-train the proposed approach on the public WebVid2M and CC3M datasets. Extensive evaluations on four downstream video-text retrieval benchmarks clearly demonstrate the effectiveness of our RegionLearner. The code will be available at https://github.com/ruiyan1995/Region_Learner.
Modern video-text retrieval frameworks basically consist of three parts: video encoder, text encoder and the similarity head. With the success on both visual and textual representation learning, transformer based encoders and fusion methods have also been adopted in the field of video-text retrieval. In this report, we present CLIP2TV, aiming at exploring where the critical elements lie in transformer based methods. To achieve this, We first revisit some recent works on multi-modal learning, then introduce some techniques into video-text retrieval, finally evaluate them through extensive experiments in different configurations. Notably, CLIP2TV achieves 52.9@R1 on MSR-VTT dataset, outperforming the previous SOTA result by 4.1%.
Video-text retrieval has many real-world applications such as media analytics, surveillance, and robotics. This paper presents the 1st place solution to the video retrieval track of the ICCV VALUE Challenge 2021. We present a simple yet effective approach to jointly tackle two video-text retrieval tasks (video retrieval and video corpus moment retrieval) by leveraging the model trained only on the video retrieval task. In addition, we create an ensemble model that achieves the new state-of-the-art performance on all four datasets (TVr, How2r, YouCook2r, and VATEXr) presented in the VALUE Challenge.
Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn cross-modal embeddings for video and text, yet without exploiting its full potential. In particular, previous losses do not take the intra-modality similarities into account, which leads to inefficient embeddings, as the same content is mapped to multiple points in the embedding space. With CrossCLR, we present a contrastive loss that fixes this issue. Moreover, we define sets of highly related samples in terms of their input embeddings and exclude them from the negative samples to avoid issues with false negatives. We show that these principles consistently improve the quality of the learned embeddings. The joint embeddings learned with CrossCLR extend the state of the art in video-text retrieval on Youcook2 and LSMDC datasets and in video captioning on Youcook2 dataset by a large margin. We also demonstrate the generality of the concept by learning improved joint embeddings for other pairs of modalities.
Employing large-scale pre-trained model CLIP to conduct video-text retrieval task (VTR) has become a new trend, which exceeds previous VTR methods. Though, due to the heterogeneity of structures and contents between video and text, previous CLIP-based models are prone to overfitting in the training phase, resulting in relatively poor retrieval performance. In this paper, we propose a multi-stream Corpus Alignment network with single gate Mixture-of-Experts (CAMoE) and a novel Dual Softmax Loss (DSL) to solve the two heterogeneity. The CAMoE employs Mixture-of-Experts (MoE) to extract multi-perspective video representations, including action, entity, scene, etc., then align them with the corresponding part of the text. In this stage, we conduct massive explorations towards the feature extraction module and feature alignment module. DSL is proposed to avoid the one-way optimum-match which occurs in previous contrastive methods. Introducing the intrinsic prior of each pair in a batch, DSL serves as a reviser to correct the similarity matrix and achieves the dual optimal match. DSL is easy to implement with only one-line code but improves significantly. The results show that the proposed CAMoE and DSL are of strong efficiency, and each of them is capable of achieving State-of-The-Art (SOTA) individually on various benchmarks such as MSR-VTT, MSVD, and LSMDC. Further, with both of them, the performance is advanced to a big extend, surpassing the previous SOTA methods for around 4.6\% R@1 in MSR-VTT.
Video-text retrieval is an important yet challenging task in vision-language understanding, which aims to learn a joint embedding space where related video and text instances are close to each other. Most current works simply measure the video-text similarity based on video-level and text-level embeddings. However, the neglect of more fine-grained or local information causes the problem of insufficient representation. Some works exploit the local details by disentangling sentences, but overlook the corresponding videos, causing the asymmetry of video-text representation. To address the above limitations, we propose a Hierarchical Alignment Network (HANet) to align different level representations for video-text matching. Specifically, we first decompose video and text into three semantic levels, namely event (video and text), action (motion and verb), and entity (appearance and noun). Based on these, we naturally construct hierarchical representations in the individual-local-global manner, where the individual level focuses on the alignment between frame and word, local level focuses on the alignment between video clip and textual context, and global level focuses on the alignment between the whole video and text. Different level alignments capture fine-to-coarse correlations between video and text, as well as take the advantage of the complementary information among three semantic levels. Besides, our HANet is also richly interpretable by explicitly learning key semantic concepts. Extensive experiments on two public datasets, namely MSR-VTT and VATEX, show the proposed HANet outperforms other state-of-the-art methods, which demonstrates the effectiveness of hierarchical representation and alignment. Our code is publicly available.
We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner. Leading approaches in the domain of video-and-language learning try to distill the spatio-temporal video features and multi-modal interaction between videos and languages from a large-scale video-text dataset. Different from them, we leverage pretrained image-language model, simplify it as a two-stage framework with co-learning of image-text and enhancing temporal relations between video frames and video-text respectively, make it able to train on comparatively small datasets. Specifically, based on the spatial semantics captured by Contrastive Language-Image Pretraining (CLIP) model, our model involves a Temporal Difference Block to capture motions at fine temporal video frames, and a Temporal Alignment Block to re-align the tokens of video clips and phrases and enhance the multi-modal correlation. We conduct thorough ablation studies, and achieve state-of-the-art performance on major text-to-video and video-to-text retrieval benchmarks, including new records of retrieval accuracy on MSR-VTT, MSVD and VATEX.
Video-text retrieval plays an essential role in multi-modal research and has been widely used in many real-world web applications. The CLIP (Contrastive Language-Image Pre-training), an image-language pre-training model, has demonstrated the power of visual concepts learning from web collected image-text datasets. In this paper, we propose a CLIP4Clip model to transfer the knowledge of the CLIP model to video-language retrieval in an end-to-end manner. Several questions are investigated via empirical studies: 1) Whether image feature is enough for video-text retrieval? 2) How a post-pretraining on a large-scale video-text dataset based on the CLIP affect the performance? 3) What is the practical mechanism to model temporal dependency between video frames? And 4) The Hyper-parameters sensitivity of the model on video-text retrieval task. Extensive experimental results present that the CLIP4Clip model transferred from the CLIP can achieve SOTA results on various video-text retrieval datasets, including MSR-VTT, MSVC, LSMDC, ActivityNet, and DiDeMo. We release our code at https://github.com/ArrowLuo/CLIP4Clip.
Our objective in this work is video-text retrieval - in particular a joint embedding that enables efficient text-to-video retrieval. The challenges in this area include the design of the visual architecture and the nature of the training data, in that the available large scale video-text training datasets, such as HowTo100M, are noisy and hence competitive performance is achieved only at scale through large amounts of compute. We address both these challenges in this paper. We propose an end-to-end trainable model that is designed to take advantage of both large-scale image and video captioning datasets. Our model is an adaptation and extension of the recent ViT and Timesformer architectures, and consists of attention in both space and time. The model is flexible and can be trained on both image and video text datasets, either independently or in conjunction. It is trained with a curriculum learning schedule that begins by treating images as 'frozen' snapshots of video, and then gradually learns to attend to increasing temporal context when trained on video datasets. We also provide a new video-text pretraining dataset WebVid-2M, comprised of over two million videos with weak captions scraped from the internet. Despite training on datasets that are an order of magnitude smaller, we show that this approach yields state-of-the-art results on standard downstream video-retrieval benchmarks including MSR-VTT, MSVD, DiDeMo and LSMDC.
Video-Text Retrieval has been a hot research topic with the growth of multimedia data on the internet. Transformer for video-text learning has attracted increasing attention due to its promising performance. However, existing cross-modal transformer approaches typically suffer from two major limitations: 1) Exploitation of the transformer architecture where different layers have different feature characteristics is limited; 2) End-to-end training mechanism limits negative sample interactions in a mini-batch. In this paper, we propose a novel approach named Hierarchical Transformer (HiT) for video-text retrieval. HiT performs Hierarchical Cross-modal Contrastive Matching in both feature-level and semantic-level, achieving multi-view and comprehensive retrieval results. Moreover, inspired by MoCo, we propose Momentum Cross-modal Contrast for cross-modal learning to enable large-scale negative sample interactions on-the-fly, which contributes to the generation of more precise and discriminative representations. Experimental results on the three major Video-Text Retrieval benchmark datasets demonstrate the advantages of our method.
Cross-modal video-text retrieval, a challenging task in the field of vision and language, aims at retrieving corresponding instance giving sample from either modality. Existing approaches for this task all focus on how to design encoding model through a hard negative ranking loss, leaving two key problems unaddressed during this procedure. First, in the training stage, only a mini-batch of instance pairs is available in each iteration. Therefore, this kind of hard negatives is locally mined inside a mini-batch while ignoring the global negative samples among the dataset. Second, there are many text descriptions for one video and each text only describes certain local features of a video. Previous works for this task did not consider to fuse the multiply texts corresponding to a video during the training. In this paper, to solve the above two problems, we propose a novel memory enhanced embedding learning (MEEL) method for videotext retrieval. To be specific, we construct two kinds of memory banks respectively: cross-modal memory module and text center memory module. The cross-modal memory module is employed to record the instance embeddings of all the datasets for global negative mining. To avoid the fast evolving of the embedding in the memory bank during training, we utilize a momentum encoder to update the features by a moving-averaging strategy. The text center memory module is designed to record the center information of the multiple textual instances corresponding to a video, and aims at bridging these textual instances together. Extensive experimental results on two challenging benchmarks, i.e., MSR-VTT and VATEX, demonstrate the effectiveness of the proposed method.
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.
Visual Semantic Embedding (VSE) is a dominant approach for vision-language retrieval, which aims at learning a deep embedding space such that visual data are embedded close to their semantic text labels or descriptions. Recent VSE models use complex methods to better contextualize and aggregate multi-modal features into holistic embeddings. However, we discover that surprisingly simple (but carefully selected) global pooling functions (e.g., max pooling) outperform those complex models, across different feature extractors. Despite its simplicity and effectiveness, seeking the best pooling function for different data modality and feature extractor is costly and tedious, especially when the size of features varies (e.g., text, video). Therefore, we propose a Generalized Pooling Operator (GPO), which learns to automatically adapt itself to the best pooling strategy for different features, requiring no manual tuning while staying effective and efficient. We extend the VSE model using this proposed GPO and denote it as VSE$\infty$. Without bells and whistles, VSE$\infty$ outperforms previous VSE methods significantly on image-text retrieval benchmarks across popular feature extractors. With a simple adaptation, variants of VSE$\infty$ further demonstrate its strength by achieving the new state of the art on two video-text retrieval datasets. Comprehensive experiments and visualizations confirm that GPO always discovers the best pooling strategy and can be a plug-and-play feature aggregation module for standard VSE models. Code and pre-trained models are available at https://vse-infty.github.io.
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
Video retrieval is a challenging research topic bridging the vision and language areas and has attracted broad attention in recent years. Previous works have been devoted to representing videos by directly encoding from frame-level features. In fact, videos consist of various and abundant semantic relations to which existing methods pay less attention. To address this issue, we propose a Visual Semantic Enhanced Reasoning Network (ViSERN) to exploit reasoning between frame regions. Specifically, we consider frame regions as vertices and construct a fully-connected semantic correlation graph. Then, we perform reasoning by novel random walk rule-based graph convolutional networks to generate region features involved with semantic relations. With the benefit of reasoning, semantic interactions between regions are considered, while the impact of redundancy is suppressed. Finally, the region features are aggregated to form frame-level features for further encoding to measure video-text similarity. Extensive experiments on two public benchmark datasets validate the effectiveness of our method by achieving state-of-the-art performance due to the powerful semantic reasoning.
In this paper, we present a framework that jointly retrieves and spatiotemporally highlights actions in videos by enhancing current deep cross-modal retrieval methods. Our work takes on the novel task of action highlighting, which visualizes where and when actions occur in an untrimmed video setting. Action highlighting is a fine-grained task, compared to conventional action recognition tasks which focus on classification or window-based localization. Leveraging weak supervision from annotated captions, our framework acquires spatiotemporal relevance maps and generates local embeddings which relate to the nouns and verbs in captions. Through experiments, we show that our model generates various maps conditioned on different actions, in which conventional visual reasoning methods only go as far as to show a single deterministic saliency map. Also, our model improves retrieval recall over our baseline without alignment by 2-3% on the MSR-VTT dataset.
Existing dominant approaches for cross-modal video-text retrieval task are to learn a joint embedding space to measure the cross-modal similarity. However, these methods rarely explore long-range dependency inside video frames or textual words leading to insufficient textual and visual details. In this paper, we propose a stacked convolutional deep encoding network for video-text retrieval task, which considers to simultaneously encode long-range and short-range dependency in the videos and texts. Specifically, a multi-scale dilated convolutional (MSDC) block within our approach is able to encode short-range temporal cues between video frames or text words by adopting different scales of kernel size and dilation size of convolutional layer. A stacked structure is designed to expand the receptive fields by repeatedly adopting the MSDC block, which further captures the long-range relations between these cues. Moreover, to obtain more robust textual representations, we fully utilize the powerful language model named Transformer in two stages: pretraining phrase and fine-tuning phrase. Extensive experiments on two different benchmark datasets (MSR-VTT, MSVD) show that our proposed method outperforms other state-of-the-art approaches.
Cross-modal retrieval between videos and texts has attracted growing attentions due to the rapid emergence of videos on the web. The current dominant approach for this problem is to learn a joint embedding space to measure cross-modal similarities. However, simple joint embeddings are insufficient to represent complicated visual and textual details, such as scenes, objects, actions and their compositions. To improve fine-grained video-text retrieval, we propose a Hierarchical Graph Reasoning (HGR) model, which decomposes video-text matching into global-to-local levels. To be specific, the model disentangles texts into hierarchical semantic graph including three levels of events, actions, entities and relationships across levels. Attention-based graph reasoning is utilized to generate hierarchical textual embeddings, which can guide the learning of diverse and hierarchical video representations. The HGR model aggregates matchings from different video-text levels to capture both global and local details. Experimental results on three video-text datasets demonstrate the advantages of our model. Such hierarchical decomposition also enables better generalization across datasets and improves the ability to distinguish fine-grained semantic differences.
Visual-semantic embedding aims to find a shared latent space where related visual and textual instances are close to each other. Most current methods learn injective embedding functions that map an instance to a single point in the shared space. Unfortunately, injective embedding cannot effectively handle polysemous instances with multiple possible meanings; at best, it would find an average representation of different meanings. This hinders its use in real-world scenarios where individual instances and their cross-modal associations are often ambiguous. In this work, we introduce Polysemous Instance Embedding Networks (PIE-Nets) that compute multiple and diverse representations of an instance by combining global context with locally-guided features via multi-head self-attention and residual learning. To learn visual-semantic embedding, we tie-up two PIE-Nets and optimize them jointly in the multiple instance learning framework. Most existing work on cross-modal retrieval focuses on image-text data. Here, we also tackle a more challenging case of video-text retrieval. To facilitate further research in video-text retrieval, we release a new dataset of 50K video-sentence pairs collected from social media, dubbed MRW (my reaction when). We demonstrate our approach on both image-text and video-text retrieval scenarios using MS-COCO, TGIF, and our new MRW dataset.
Hashing has been widely applied to multimodal retrieval on large-scale multimedia data due to its efficiency in computation and storage. In this article, we propose a novel deep semantic multimodal hashing network (DSMHN) for scalable image-text and video-text retrieval. The proposed deep hashing framework leverages 2-D convolutional neural networks (CNN) as the backbone network to capture the spatial information for image-text retrieval, while the 3-D CNN as the backbone network to capture the spatial and temporal information for video-text retrieval. In the DSMHN, two sets of modality-specific hash functions are jointly learned by explicitly preserving both intermodality similarities and intramodality semantic labels. Specifically, with the assumption that the learned hash codes should be optimal for the classification task, two stream networks are jointly trained to learn the hash functions by embedding the semantic labels on the resultant hash codes. Moreover, a unified deep multimodal hashing framework is proposed to learn compact and high-quality hash codes by exploiting the feature representation learning, intermodality similarity-preserving learning, semantic label-preserving learning, and hash function learning with different types of loss functions simultaneously. The proposed DSMHN method is a generic and scalable deep hashing framework for both image-text and video-text retrievals, which can be flexibly integrated with different types of loss functions. We conduct extensive experiments for both single modal- and cross-modal-retrieval tasks on four widely used multimodal-retrieval data sets. Experimental results on both image-text- and video-text-retrieval tasks demonstrate that the DSMHN significantly outperforms the state-of-the-art methods.