Most existing video summarisation methods are based on either supervised or unsupervised learning. In this paper, we propose a reinforcement learning-based weakly supervised method that exploits easy-to-obtain, video-level category labels and encourages summaries to contain category-related information and maintain category recognisability. Specifically, We formulate video summarisation as a sequential decision-making process and train a summarisation network with deep Q-learning (DQSN). A companion classification network is also trained to provide rewards for training the DQSN. With the classification network, we develop a global recognisability reward based on the classification result. Critically, a novel dense ranking-based reward is also proposed in order to cope with the temporally delayed and sparse reward problems for long sequence reinforcement learning. Extensive experiments on two benchmark datasets show that the proposed approach achieves state-of-the-art performance.
University of the Witwatersrand（金山大学）；School of Computer Science and Applied Mathematics（计算机科学与应用数学系）
Video summarisation can be posed as the task of extracting important parts of a video in order to create an informative summary of what occurred in the video. In this paper we introduce SummaryNet as a supervised learning framework for automated video summarisation. SummaryNet employs a two-stream convolutional network to learn spatial (appearance) and temporal (motion) representations. It utilizes an encoder-decoder model to extract the most salient features from the learned video representations. Lastly, it uses a sigmoid regression network with bidirectional long short-term memory cells to …
NICTA；University of Queensland（昆士兰大学）；Queensland University of Technology（昆士兰科技大学）
We present a novel approach to video summarisation that makes use of a Bag-of-visual-Textures (BoT) approach. Two systems are proposed, one based solely on the BoT approach and another which exploits both colour information and BoT features. On 50 short-term videos from the Open Video Project we show that our BoT and fusion systems both achieve state-of-the-art performance, obtaining an average F-measure of 0.83 and 0.86 respectively, a relative improvement of 9% and 13% when compared to the previous state-of-the-art. When applied to a new underwater surveillance dataset containing 33 long-ter…
Queen Mary University of London（伦敦玛丽女王大学）；The Chinese University of Hong Kong（香港中文大学）
Many visual surveillance tasks, e.g.video summarisation, is conventionally accomplished through analysing imagerybased features. Relying solely on visual cues for public surveillance video understanding is unreliable, since visual observations obtained from public space CCTV video data are often not sufficiently trustworthy and events of interest can be subtle. On the other hand, non-visual data sources such as weather reports and traffic sensory signals are readily accessible but are not explored jointly to complement visual data for video content analysis and summarisation. In this paper, we…
Imperial College London（伦敦帝国学院）；University College London（伦敦大学学院）；Samsung AI Center Cambridge（三星剑桥人工智能中心）
For real-time semantic video segmentation, most recent works utilised a dynamic framework with a key scheduler to make online key/non-key decisions. Some works used a fixed key scheduling policy, while others proposed adaptive key scheduling methods based on heuristic strategies, both of which may lead to suboptimal global performance. To overcome this limitation, we model the online key decision process in dynamic video segmentation as a deep reinforcement learning problem and learn an efficient and effective scheduling policy from expert information about decision history and from the proces…
Shandong University（山东大学）；Tencent AI Lab（腾讯人工智能实验室）
In this paper, the problem of describing visual contents of a video sequence with natural language is addressed. Unlike previous video captioning work mainly exploiting the cues of video contents to make a language description, we propose a reconstruction network (RecNet) in a novel encoder-decoder-reconstructor architecture, which leverages both forward (video to sentence) and backward (sentence to video) flows for video captioning. Specifically, the encoder-decoder component makes use of the forward flow to produce a sentence description based on the encoded video semantic features. Two type…
Known-item video search is effective with human-in-the-loop to interactively investigate the search result and refine the initial query. Nevertheless, when the first few pages of results are swamped with visually similar items, or the search target is hidden deep in the ranked list, finding the know-item target usually requires a long duration of browsing and result inspection. This paper tackles the problem by reinforcement learning, aiming to reach a search target within a few rounds of interaction by long-term learning from user feedbacks. Specifically, the system interactively plans for na…
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
School of Automation, Southeast University, Nanjing, China；Baidu Inc, Beijing, China；College of Information Science \& Electronic Engineering, Zhejiang University, Hangzhou, China
The University of Sydney（悉尼大学）；International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；University of Rochester（罗切斯特大学）
Multimodal summarisation with multimodal output is drawing increasing attention due to the rapid growth of multimedia data. While several methods have been proposed to summarise visual-text contents, their multimodal outputs are not succinct enough at an extreme level to address the information overload issue. To the end of extreme multimodal summarisation, we introduce a new task, eXtreme Multimodal Summarisation with Multimodal Output (XMSMO) for the scenario of TL;DW - Too Long; Didn't Watch, akin to TL;DR. XMSMO aims to summarise a video-document pair into a summary with an extremely short…
DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning
Georgia Institute of Technology（佐治亚理工学院）；Rice University（Rice大学）；Johns Hopkins University（约翰霍普金斯大学）；University of California, Irvine（加州大学 Irvine分校）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
The University of Adelaide（阿德莱德大学）；Apollo Labs（阿波罗实验室）
The ability to use inductive reasoning to extract general rules from multiple observations is a vital indicator of intelligence. As humans, we use this ability to not only interpret the world around us, but also to predict the outcomes of the various interactions we experience. Generalising over multiple observations is a task that has historically presented difficulties for machines to grasp, especially when requiring computer vision. In this paper, we propose a model that can extract general rules from video demonstrations by simultaneously performing summarisation and translation. Our appro…
Video is an essential imaging modality for diagnostics, e.g. in ultrasound imaging, for endoscopy, or movement assessment. However, video hasn't received a lot of attention in the medical image analysis community. In the clinical practice, it is challenging to utilise raw diagnostic video data efficiently as video data takes a long time to process, annotate or audit. In this paper we introduce a novel, fully automatic video summarization method that is tailored to the needs of medical video data. Our approach is framed as reinforcement learning problem and produces agents focusing on the prese…
Intelligent video summarization algorithms allow to quickly convey the most relevant information in videos through the identification of the most essential and explanatory content while removing redundant video frames. In this paper, we introduce the 3DST-UNet-RL framework for video summarization. A 3D spatio-temporal U-Net is used to efficiently encode spatio-temporal information of the input videos for downstream reinforcement learning (RL). An RL agent learns from spatio-temporal latent scores and predicts actions for keeping or rejecting a video frame in a video summary. We investigate if …
Concordia University（康考迪亚大学）；University of Arkansas（阿肯色大学）；Clemson University（克莱姆森大学）；Carnegie Mellon University（卡内基梅隆大学）
This paper presents a novel approach to synthesize automatically age-progressed facial images in video sequences using Deep Reinforcement Learning. The proposed method models facial structures and the longitudinal face-aging process of given subjects coherently across video frames. The approach is optimized using a long-term reward, Reinforcement Learning function with deep feature extraction from Deep Convolutional Neural Network. Unlike previous age-progression methods that are only able to synthesize an aged likeness of a face from a single input image, the proposed approach is capable of a…
Baidu Inc.（百度公司）；Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology（哈尔滨工业大学社会计算与信息检索研究中心）
The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or exhaustively ranking all possible clip-sentence pairs in a pre-segmented video, which inevitably suffer from exhaustively enumerated candidates. To alleviate this problem, we formulate this task as a problem of sequential decision making by learning an agent which regulates the temporal grounding boundaries progressively based on its policy. Specifically, we propose…
VideoSSR: Video Self-Supervised Reinforcement Learning
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）；Wuhan University（武汉大学）
Universidade Federal de Minas Gerais (UFMG)（米纳斯吉拉斯联邦大学（UFMG））；Lancaster University（兰卡斯特大学）
The rapid increase in the amount of published visual data and the limited time of users bring the demand for processing untrimmed videos to produce shorter versions that convey the same information. Despite the remarkable progress that has been made by summarization methods, most of them can only select a few frames or skims, which creates visual gaps and breaks the video context. In this paper, we present a novel methodology based on a reinforcement learning formulation to accelerate instructional videos. Our approach can adaptively select frames that are not relevant to convey the informatio…
University of Edinburgh（爱丁堡大学）；School of Informatics（信息学院）
We consider the challenging problem of zero-shot video object segmentation (VOS). That is, segmenting and tracking multiple moving objects within a video fully automatically, without any manual initialization. We treat this as a grouping problem by exploiting object proposals and making a joint inference about grouping over both space and time. We propose a network architecture for tractably performing proposal selection and joint grouping. Crucially, we then show how to train this network with reinforcement learning so that it learns to perform the optimal non-myopic sequence of grouping deci…
Sun Yat-sen University（中山大学）；Beihang University（北京航空航天大学）；DarkMatter AI Research（DarkMatter AI研究院）
Temporally language grounding in untrimmed videos is a newly-raised task in video understanding. Most of the existing methods suffer from inferior efficiency, lacking interpretability, and deviating from the human perception mechanism. Inspired by human's coarse-to-fine decision-making paradigm, we formulate a novel Tree-Structured Policy based Progressive Reinforcement Learning (TSP-PRL) framework to sequentially regulate the temporal boundary by an iterative refinement process. The semantic concepts are explicitly represented as the branches in the policy, which contributes to efficiently de…
Fudan University（复旦大学）；Imperial College London（伦敦帝国理工学院）；Alibaba (Beijing) Software Service Company Limited（阿里巴巴（北京）软件服务有限公司）；University of Colorado Boulder（科罗拉多大学博尔德分校）；University of Michigan（密歇根大学）；Microsoft Research Asia（微软亚洲研究院）
Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its adoption in energy-constrained applications. Motivated by the observation of high and variable spatial redundancy and temporal dynamics in video data streams, we design and evaluate an adaptive-resolution optimization framework to minimize the energy use of multi-task video analytics pipelines. Instead of heuristically tuning the input data resolution of individual…
VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
Shanghai AI Laboratory（上海人工智能实验室）；Nanjing University（南京大学）；Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）；Shanghai Innovation Institute（上海创新研究院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Queen Mary University of London（伦敦玛丽女王大学）
Video summarization aims to facilitate large-scale video browsing by producing short, concise summaries that are diverse and representative of original videos. In this paper, we formulate video summarization as a sequential decision-making process and develop a deep summarization network (DSN) to summarize videos. DSN predicts for each video frame a probability, which indicates how likely a frame is selected, and then takes actions based on the probability distributions to select frames, forming video summaries. To train our DSN, we propose an end-to-end, reinforcement learning-based framework…
Beihang University（北京航空航天大学）；Tencent AI LAB（腾讯AI实验室）
Although end-to-end (E2E) learning has led to impressive progress on a variety of visual understanding tasks, it is often impeded by hardware constraints (e.g., GPU memory) and is prone to overfitting. When it comes to video captioning, one of the most challenging benchmark tasks in computer vision, those limitations of E2E learning are especially amplified by the fact that both the input videos and output captions are lengthy sequences. Indeed, state-of-the-art methods for video captioning process video frames by convolutional neural networks and generate captions by unrolling recurrent neura…
Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）；Universidade Federal de Viçosa（维索萨联邦大学）；Lancaster University（兰卡斯特大学）
The growth of videos in our digital age and the users' limited time raise the demand for processing untrimmed videos to produce shorter versions conveying the same information. Despite the remarkable progress that summarization methods have made, most of them can only select a few frames or skims, creating visual gaps and breaking the video context. This paper presents a novel weakly-supervised methodology based on a reinforcement learning formulation to accelerate instructional videos using text. A novel joint reward function guides our agent to select which frames to remove and reduce the in…
Northwestern University（西北大学）；University of California, Riverside（加州大学河滨分校）
For many applications with limited computation, communication, storage and energy resources, there is an imperative need of computer vision methods that could select an informative subset of the input video for efficient processing at or near real time. In the literature, there are two relevant groups of approaches: generating a trailer for a video or fast-forwarding while watching/processing the video. The first group is supported by video summarization techniques, which require processing of the entire video to select an important subset for showing to users. In the second group, current fas…
VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning
MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS部）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Shenzhen Institute of Advanced Technology (SIAT), Chinese Academy of Sciences（中国科学院深圳先进技术研究所）
Beihang University（北京航空航天大学）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
Adversarial attacks on video recognition models have been explored recently. However, most existing works treat each video frame equally and ignore their temporal interactions. To overcome this drawback, a few methods try to select some key frames and then perform attacks based on them. Unfortunately, their selection strategy is independent of the attacking step, therefore the resulting performance is limited. Instead, we argue the frame selection phase is closely relevant with the attacking phase. The key frames should be adjusted according to the attacking results. For that, we formulate the…
Rice University（莱斯大学）；IIT-Delhi（德里印度理工学院）；Olin College of Engineering（奥林工程学院）；Baylor College of Medicine（贝勒医学院）
Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks. In such framework, besides the regular ConvNets responsible for RGB frame inputs, a second network is introduced to handle the temporal representation, usually the optical flow (OF). However, OF or other task-oriented flow is computationally costly, and is thus typically pre-computed. Critically, this prevents the two-stream approach from being applied to reinforcement learning (RL) applications such as video game playing, where the next state…
University of California, Irvine（加利福尼亚大学尔湾分校）；Carnegie Mellon University（卡内基梅隆大学）
We formulate tracking as an online decision-making process, where a tracking agent must follow an object despite ambiguous image frames and a limited computational budget. Crucially, the agent must decide where to look in the upcoming frames, when to reinitialize because it believes the target has been lost, and when to update its appearance model for the tracked object. Such decisions are typically made heuristically. Instead, we propose to learn an optimal decision-making policy by formulating tracking as a partially observable decision-making process (POMDP). We learn policies with deep rei…
Claim-Level Rubric Rewards for Video Caption Reinforcement Learning
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；University of Chinese Academy of Sciences（中国科学院大学）；LLM Department, Tencent（腾讯大语言模型部）
