TVSum: Summarizing web videos using titles

By Yale Song, Jordi Vallmitjana, Amanda Stent, Alejandro Jaimes. Computer Vision and Pattern Recognition, 2015

773 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/cbf89cb4e107fb59e119ae619bcfe48e1964e033

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Enhancing Video Summarization via Vision-Language Embedding (2017, background): “Note that there exist other popular benchmarks for video summarization, including SumMe [8] and TVSUM [34] datasets.”
Unsupervised Video Summarization with Adversarial LSTM Networks (2017, methodology): “2) TVSum contains 50 videos from YouTube.”
Deep Attentive Video Summarization With Distribution Consistency Learning (2020, methodology): “1) Data Sets: We evaluate the proposed ADSum method on three publicly available benchmark data sets of video summarization: SumMe [12], TVSum [13], and YouTube [21].”
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding (2023, background): “There have been miscellaneous time-sensitive video tasks, including temporal video grounding [27, 49], dense video captioning [46, 52, 62], video summarization [1, 8, 41, 58], video highlight detection [15, 30], and step localization [5, 39, 55], etc.”
Video Summarization With Attention-Based Encoder–Decoder Networks (2017, methodology): “Note that this is exactly the 0/1 knapsack problem, which can be solved by the dynamic programming method [25].”
Multimodal Abstractive Summarization for How2 Videos (2019, background): “Video summarization is the task of producing a compact version of the video (visual summary) by encapsulating the most informative parts (Money and Agius, 2008; Lu and Grauman, 2013; Gygli et al., 2014; Song et al., 2015; Sah et al., 2017).”
Video Summarization Using Deep Neural Networks: A Survey (2021, methodology): “This work started by evaluating the performance of five publicly-available methods under a large-scale experimental setting with 50 randomlycreated data splits of the SumMe and TVSum datasets, where the performance is evaluated using F-Score.”
Dense-Captioning Events in Videos (2017, methodology): “Meanwhile, others have utilized text inputs from user studies to guide the selection process [34, 23].”
Less Is More: Picking Informative Frames for Video Captioning (2018, background): “[31] considered images related to the video title that can serve as a proxy for important visual concepts, so they developed a co-archetypal analysis technique that learns canonical visual concepts shared between video and images, and used it to summarize videos.”
Video Summarization with Long Short-Term Memory (2016, methodology): “Datasets We evaluate the performance of our models on two video datasets, SumMe [17] and TVSum [35].”
A Practical Online Framework for Extracting Running Video Summaries under a Fixed Memory Budget (2021, methodology): “For each video in SumMe and TVSum50 we ﬁx the size of a video snippet to 2 seconds (as suggested in TVSum50 [27]) and evaluate with the two diﬀerent budget size.”
Learning Temporal Regularity in Video Sequences (2016, background): “Automatic segmentation of ‘meaningful’ moments in such videos without supervision or with very limited supervision is a fundamental problem for various computer vision applications such as video annotation [2], summarization [3, 4], indexing or temporal segmentation [5], anomaly detection [6], and a”
Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language (2019, background): “2016), video summarization (Song et al. 2015; Chu, Song, and Jaimes 2015), and moment localization with natural language (Gao et al.”
Viewpoint-Aware Video Summarization (2018, background): “Unsupervised summarization [28, 25, 24, 26, 1, 8, 43, 14, 17, 18, 36, 27, 6] that creates a summary using specific selection criteria, has been conventionally studied.”
Localizing Moments in Video with Natural Language (2017, neutral): “Though most summarization algorithms do not include textual input ([3, 9, 10, 52, 53]), some use text in the form of video titles [21, 41] or user queries in the form of category labels to guide content selection [37].”
Pano2Vid: Automatic Cinematography for Watching 360° Videos (2016, methodology): “Among these, our proposed AutoCam shares with [10–12, 18, 19] the idea of using user-generated visual content from the web as exemplars for informative content.”
Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward (2017, methodology): “Following (Song et al. 2015; Zhang et al. 2016b), we convert importance scores to shot-based summaries for evaluation.”
Textually Customized Video Summaries (2017, methodology): “rally aligned texts, and trains an objective function comprising of predened terms. While both methods are conceptually similar, our method focuses on the semantic aspect of summarization. Song etal .[33]proposeatitlebasedvideosummarization. Their idea is to query video titles through web search eng”