The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods depend heavily either on supervised annotations or on attention-based models, which are computationally expensive and brittle in the face of distribution shifts that hinder cross-domain applicability across datasets. We introduce a pioneering self-supervised video summarization model that captures both spatial and temporal dependencies without the overhead of attention, RNNs, or transformers. Our framework integrates a novel set of Markov process-driven loss metrics and a two-stage self supervised learning paradigm that ensures both performance and efficiency. Our approach achieves state-of-the-art performance on the SUMME and TVSUM datasets, outperforming all existing unsupervised methods. It also rivals the best supervised models, demonstrating the potential for efficient, annotation-free architectures. This paves the way for more generalizable video summarization techniques and challenges the prevailing reliance on complex architectures.
With the exponential growth of video data, video summarization techniques are urgently needed for reducing people’s efforts in the videos' content exploration by generating succinct but informative summaries from original lengthy videos. Though supervised video summarization approaches have demonstrated the state-of-the-art performance, unsupervised methods are still highly demanded due to resourcefully expensive human annotations and the subjectiveness of video summarization tasks. In this paper, a novel unsupervised-based Deep Self-attention Recurrent summarization network with Reinforcement Learning (DSR-RL) for video summarization is proposed. The model can learn the input video sequence and suggest the key-shot summary without additional human annotations by integrating self-attention, BRNN, and reinforcement learning mechanisms. The DSR-RL improves not only importance score through the attention map vector of self-attention network but also the diversity of summaries via the reward function of reinforcement learning. Our method outperforms the state-of-the-art unsupervised video summarization methods on both SumMe and TVSum datasets. The source code is available at https://github.com/phaphuang/DSR-RL.
Video summarization mainly aims to produce a compact, short, informative, and representative synopsis of raw videos, which is of great importance for browsing, analyzing, and understanding video content. Dominant video summarization approaches are generally based on recurrent or convolutional neural networks, even recent encoder-only transformers. We propose using full transformer as an alternative architecture to perform video summarization. The full transformer with an encoder-decoder structure, specifically designed for handling sequence transduction problems, is naturally suitable for video summarization tasks. This work considers supervised video summarization and casts it as a sequence-to-sequence learning problem. Our key idea is to directly apply the full transformer to the video summarization task, which is intuitively sound and effective. Also, considering the efficiency problem, we replace full attention with the combination of local and global sparse attention, which enables modeling long-range dependencies while reducing computational costs. Based on this, we propose a transformer-like architecture, named FullTransNet, which has a full encoder-decoder structure with local-global sparse attention for video summarization. Specifically, both the encoder and decoder in FullTransNet are stacked the same way as ones in the vanilla transformer, and the local-global sparse attention is used only at the encoder side. Extensive experiments on two public multimedia benchmark datasets SumMe and TVSum demonstrate that our proposed model can outperform other video summarization approaches, achieving F-Measures of 54.4% on SumMe and 63.9% on TVSum with relatively lower compute and memory requirements, verifying its effectiveness and efficiency. The code and models are publicly available on GitHub.
Video summarization aims to generate a concise representation of a video, capturing its essential content and key moments while reducing its overall length. Although several methods employ attention mechanisms to handle long-term dependencies, they often fail to capture the visual significance inherent in frames. To address this limitation, we propose a CNN-based SpatioTemporal Attention (CSTA) method that stacks each feature of frames from a single video to form image-like frame representations and applies 2D CNN to these frame features. Our methodology relies on CNN to comprehend the inter and intra-frame relations and to find crucial attributes in videos by exploiting its ability to learn absolute positions within images. In contrast to previous work compromising efficiency by designing additional modules to focus on spatial importance, CSTA requires minimal computational overhead as it uses CNN as a sliding window. Extensive experiments on two benchmark datasets (SumMe and TVSum) demonstrate that our proposed approach achieves state-of-the-art performance with fewer MACs compared to previous methods. Codes are available at https://github.com/thswodnjs3/CSTA.
Current video summarization methods rely heavily on supervised computer vision techniques, which demands time-consuming and subjective manual annotations. To overcome these limitations, we investigated self-supervised video summarization. Inspired by the success of Large Language Models (LLMs), we explored the feasibility in transforming the video summarization task into a Natural Language Processing (NLP) task. By leveraging the advantages of LLMs in context understanding, we aim to enhance the effectiveness of self-supervised video summarization. Our method begins by generating captions for individual video frames, which are then synthesized into text summaries by LLMs. Subsequently, we measure semantic distance between the captions and the text summary. Notably, we propose a novel loss function to optimize our model according to the diversity of the video. Finally, the summarized video can be generated by selecting the frames with captions similar to the text summary. Our method achieves state-of-the-art performance on the SumMe dataset in rank correlation coefficients. In addition, our method has a novel feature of being able to achieve personalized summarization.
The goal of multimodal summarization is to extract the most important information from different modalities to form output summaries. Unlike the unimodal summarization, the multimodal summarization task explicitly leverages cross-modal information to help generate more reliable and high-quality summaries. However, existing methods fail to leverage the temporal correspondence between different modalities and ignore the intrinsic correlation between different samples. To address this issue, we introduce Align and Attend Multimodal Summarization (A2Summ), a unified multimodal transformer-based model which can effectively align and attend the multimodal input. In addition, we propose two novel contrastive losses to model both inter-sample and intra-sample correlations. Extensive experiments on two standard video summarization datasets (TVSum and SumMe) and two multimodal summarization datasets (Daily Mail and CNN) demonstrate the superiority of A2Summ, achieving state-of-the-art performances on all datasets. Moreover, we collected a large-scale multimodal summarization dataset BLiSS, which contains livestream videos and transcribed texts with annotated summaries. Our code and dataset are publicly available at ~\url{https://boheumd.github.io/A2Summ/}.
In this paper, we propose a dynamic graph modeling approach to learn spatial-temporal representations for video summarization. Most existing video summarization methods extract image-level features with ImageNet pre-trained deep models. Differently, our method exploits object-level and relation-level information to capture spatial-temporal dependencies. Specifically, our method builds spatial graphs on the detected object proposals. Then, we construct a temporal graph by using the aggregated representations of spatial graphs. Afterward, we perform relational reasoning over spatial and temporal graphs with graph convolutional networks and extract spatial-temporal representations for importance score prediction and key shot selection. To eliminate relation clutters caused by densely connected nodes, we further design a self-attention edge pooling module, which disregards meaningless relations of graphs. We conduct extensive experiments on two popular benchmarks, including the SumMe and TVSum datasets. Experimental results demonstrate that the proposed method achieves superior performance against state-of-the-art video summarization methods.
Modern video summarization methods are based on deep neural networks that require a large amount of annotated data for training. However, existing datasets for video summarization are small-scale, easily leading to over-fitting of the deep models. Considering that the annotation of large-scale datasets is time-consuming, we propose a multimodal self-supervised learning framework to obtain semantic representations of videos, which benefits the video summarization task. Specifically, the self-supervised learning is conducted by exploring the semantic consistency between the videos and text in both coarse-grained and fine-grained fashions, as well as recovering masked frames in the videos. The multimodal framework is trained on a newly-collected dataset that consists of video-text pairs. Additionally, we introduce a progressive video summarization method, where the important content in a video is pinpointed progressively to generate better summaries. Extensive experiments have proved the effectiveness and superiority of our method in rank correlation coefficients and F-score.
Video summarization aims to automatically generate a summary (storyboard or video skim) of a video, which can facilitate large-scale video retrieval and browsing. Most of the existing methods perform video summarization on individual videos, which neglects the correlations among similar videos. Such correlations, however, are also informative for video understanding and video summarization. To address this limitation, we propose Video Joint Modelling based on Hierarchical Transformer (VJMHT) for co-summarization, which takes into consideration the semantic dependencies across videos. Specifically, VJMHT consists of two layers of Transformer: the first layer extracts semantic representation from individual shots of similar videos, while the second layer performs shot-level video joint modelling to aggregate cross-video semantic information. By this means, complete cross-video high-level patterns are explicitly modelled and learned for the summarization of individual videos. Moreover, Transformer-based video representation reconstruction is introduced to maximize the high-level similarity between the summary and the original video. Extensive experiments are conducted to verify the effectiveness of the proposed modules and the superiority of VJMHT in terms of F-measure and rank-based evaluation.
Video summarization methods are usually classified into shot-level or frame-level methods, which are individually used in a general way. This paper investigates the underlying complementarity between the frame-level and shot-level methods, and a stacking ensemble approach is proposed for supervised video summarization. Firstly, we build up a stacking model to predict both the key frame probabilities and the temporal interest segments simultaneously. The two components are then combined via soft decision fusion to obtain the final scores of each frame in the video. A joint loss function is proposed for the model training. The ablation experimental results show that the proposed method outperforms both the two corresponding individual method. Furthermore, extensive experimental results on two benchmark datasets shows its superior performance in comparison with the state-of-the-art methods.
Although video summarization has achieved tremendous success benefiting from Recurrent Neural Networks (RNN), RNN-based methods neglect the global dependencies and multi-hop relationships among video frames, which limits the performance. Transformer is an effective model to deal with this problem, and surpasses RNN-based methods in several sequence modeling tasks, such as machine translation, video captioning, \emph{etc}. Motivated by the great success of transformer and the natural structure of video (frame-shot-video), a hierarchical transformer is developed for video summarization, which can capture the dependencies among frame and shots, and summarize the video by exploiting the scene information formed by shots. Furthermore, we argue that both the audio and visual information are essential for the video summarization task. To integrate the two kinds of information, they are encoded in a two-stream scheme, and a multimodal fusion mechanism is developed based on the hierarchical transformer. In this paper, the proposed method is denoted as Hierarchical Multimodal Transformer (HMT). Practically, extensive experiments show that HMT surpasses most of the traditional, RNN-based and attention-based video summarization methods.
Increasing volume of user-generated human-centric video content and their applications, such as video retrieval and browsing, require compact representations that are addressed by the video summarization literature. Current supervised studies formulate video summarization as a sequence-to-sequence learning problem and the existing solutions often neglect the surge of human-centric view, which inherently contains affective content. In this study, we investigate the affective-information enriched supervised video summarization task for human-centric videos. First, we train a visual input-driven state-of-the-art continuous emotion recognition model (CER-NET) on the RECOLA dataset to estimate emotional attributes. Then, we integrate the estimated emotional attributes and the high-level representations from the CER-NET with the visual information to define the proposed affective video summarization architectures (AVSUM). In addition, we investigate the use of attention to improve the AVSUM architectures and propose two new architectures based on temporal attention (TA-AVSUM) and spatial attention (SA-AVSUM). We conduct video summarization experiments on the TvSum database. The proposed AVSUM-GRU architecture with an early fusion of high level GRU embeddings and the temporal attention based TA-AVSUM architecture attain competitive video summarization performances by bringing strong performance improvements for the human-centric videos compared to the state-of-the-art in terms of F-score and self-defined face recall metrics.
A generic video summary is an abridged version of a video that conveys the whole story and features the most important scenes. Yet the importance of scenes in a video is often subjective, and users should have the option of customizing the summary by using natural language to specify what is important to them. Further, existing models for fully automatic generic summarization have not exploited available language models, which can serve as an effective prior for saliency. This work introduces CLIP-It, a single framework for addressing both generic and query-focused video summarization, typically approached separately in the literature. We propose a language-guided multimodal transformer that learns to score frames in a video based on their importance relative to one another and their correlation with a user-defined query (for query-focused summarization) or an automatically generated dense video caption (for generic video summarization). Our model can be extended to the unsupervised setting by training without ground-truth supervision. We outperform baselines and prior work by a significant margin on both standard video summarization datasets (TVSum and SumMe) and a query-focused video summarization dataset (QFVS). Particularly, we achieve large improvements in the transfer setting, attesting to our method's strong generalization capabilities.
The assignment of importance scores to particular frames or (short) segments in a video is crucial for summarization, but also a difficult task. Previous work utilizes only one source of visual features. In this paper, we suggest a novel model architecture that combines three feature sets for visual content and motion to predict importance scores. The proposed architecture utilizes an attention mechanism before fusing motion features and features representing the (static) visual content, i.e., derived from an image classification model. Comprehensive experimental evaluations are reported for two well-known datasets, SumMe and TVSum. In this context, we identify methodological issues on how previous work used these benchmark datasets, and present a fair evaluation scheme with appropriate data splits that can be used in future work. When using static and motion features with parallel attention mechanism, we improve state-of-the-art results for SumMe, while being on par with the state of the art for the other dataset.
Automatic video summarization is still an unsolved problem due to several challenges. The currently available datasets either have very short videos or have few long videos of only a particular type. We introduce a new benchmarking video dataset called VISIOCITY (VIdeo SummarIzatiOn based on Continuity, Intent and DiversiTY) which comprises of longer videos across six different categories with dense concept annotations capable of supporting different flavors of video summarization and other vision problems. For long videos, human reference summaries necessary for supervised video summarization techniques are difficult to obtain. We explore strategies to automatically generate multiple reference summaries from indirect ground truth present in VISIOCITY. We show that these summaries are at par with human summaries. We also present a study of different desired characteristics of a good summary and demonstrate how it is normal to have two good summaries with different characteristics. Thus we argue that evaluating a summary against one or more human summaries and using a single measure has its shortcomings. We propose an evaluation framework for better quantitative assessment of summary quality which is closer to human judgment. Lastly, we present insights into how a model can be enhanced to yield better summaries. Sepcifically, when multiple diverse ground truth summaries can exist, learning from them individually and using a combination of loss functions measuring different characteristics is better than learning from a single combined (oracle) ground truth summary using a single loss function. We demonstrate the effectiveness of doing so as compared to some of the representative state of the art techniques tested on VISIOCITY. We release VISIOCITY as a benchmarking dataset and invite researchers to test the effectiveness of their video summarization algorithms on VISIOCITY.
In this paper, we propose a Detect-to-Summarize network (DSNet) framework for supervised video summarization. Our DSNet contains anchor-based and anchor-free counterparts. The anchor-based method generates temporal interest proposals to determine and localize the representative contents of video sequences, while the anchor-free method eliminates the pre-defined temporal proposals and directly predicts the importance scores and segment locations. Different from existing supervised video summarization methods which formulate video summarization as a regression problem without temporal consistency and integrity constraints, our interest detection framework is the first attempt to leverage temporal consistency via the temporal interest detection formulation. Specifically, in the anchor-based approach, we first provide a dense sampling of temporal interest proposals with multi-scale intervals that accommodate interest variations in length, and then extract their long-range temporal features for interest proposal location regression and importance prediction. Notably, positive and negative segments are both assigned for the correctness and completeness information of the generated summaries. In the anchor-free approach, we alleviate drawbacks of temporal proposals by directly predicting importance scores of video frames and segment locations. Particularly, the interest detection framework can be flexibly plugged into off-the-shelf supervised video summarization methods. We evaluate the anchor-based and anchor-free approaches on the SumMe and TVSum datasets. Experimental results clearly validate the effectiveness of the anchor-based and anchor-free approaches.
Video summarization aims to select representative frames to retain high-level information, which is usually solved by predicting the segment-wise importance score via a softmax function. However, softmax function suffers in retaining high-rank representations for complex visual or sequential information, which is known as the Softmax Bottleneck problem. In this paper, we propose a novel framework named Dual Mixture Attention (DMASum) model with Meta Learning for video summarization that tackles the softmax bottleneck problem, where the Mixture of Attention layer (MoA) effectively increases the model capacity by employing twice self-query attention that can capture the second-order changes in addition to the initial query-key attention, and a novel Single Frame Meta Learning rule is then introduced to achieve more generalization to small datasets with limited training sources. Furthermore, the DMASum significantly exploits both visual and sequential attention that connects local key-frame and global attention in an accumulative way. We adopt the new evaluation protocol on two public datasets, SumMe, and TVSum. Both qualitative and quantitative experiments manifest significant improvements over the state-of-the-art methods.
Conventional video summarization approaches based on reinforcement learning have the problem that the reward can only be received after the whole summary is generated. Such kind of reward is sparse and it makes reinforcement learning hard to converge. Another problem is that labelling each frame is tedious and costly, which usually prohibits the construction of large-scale datasets. To solve these problems, we propose a weakly supervised hierarchical reinforcement learning framework, which decomposes the whole task into several subtasks to enhance the summarization quality. This framework consists of a manager network and a worker network. For each subtask, the manager is trained to set a subgoal only by a task-level binary label, which requires much fewer labels than conventional approaches. With the guide of the subgoal, the worker predicts the importance scores for video frames in the subtask by policy gradient according to both global reward and innovative defined sub-rewards to overcome the sparse problem. Experiments on two benchmark datasets show that our proposal has achieved the best performance, even better than supervised approaches.
In this paper, we propose Test-Time Training, a general approach for improving the performance of predictive models when training and test data come from different distributions. We turn a single unlabeled test sample into a self-supervised learning problem, on which we update the model parameters before making a prediction. This also extends naturally to data in an online stream. Our simple approach leads to improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts.
In this paper, we address the problem of unsupervised video summarization that automatically extracts key-shots from an input video. Specifically, we tackle two critical issues based on our empirical observations: (i) Ineffective feature learning due to flat distributions of output importance scores for each frame, and (ii) training difficulty when dealing with long-length video inputs. To alleviate the first problem, we propose a simple yet effective regularization loss term called variance loss. The proposed variance loss allows a network to predict output scores for each frame with high discrepancy which enables effective feature learning and significantly improves model performance. For the second problem, we design a novel two-stream network named Chunk and Stride Network (CSNet) that utilizes local (chunk) and global (stride) temporal view on the video features. Our CSNet gives better summarization results for long-length videos compared to the existing methods. In addition, we introduce an attention mechanism to handle the dynamic information in videos. We demonstrate the effectiveness of the proposed methods by conducting extensive ablation studies and show that our final model achieves new state-of-the-art results on two benchmark datasets.