Search

Short-form video content has become increasingly popular and influential in recent years. Its concise yet engaging format aligns well with todays' fast-paced and on-the-go lifestyles, making it a dominating trend in the digital world. As one of the front runners in the short video platform space, ByteDance has been highly successful in delivering a one-of-a-kind short video experience and attracting billions of users worldwide. One key contributing factor is its advanced end-to-end personalized short video playback technology, where we pioneered and developed the new technical field over the past five years to optimize user experience. This paper introduces the major concepts and methodologies of this personalized video playback technology that distinguish it from traditional multimedia technologies. More details, including goal setting, iterative process, modeling, experimental methods and required supporting systems, are also provided to encourage deeper research in this area.

Personalized search has been extensively studied in various applications, including web search, e-commerce, social networks, etc. With the soaring popularity of short-video platforms, exemplified by TikTok and Kuaishou, the question arises: can personalization elevate the realm of short-video search, and if so, which techniques hold the key? In this work, we introduce $\text{PR}^2$, a novel and comprehensive solution for personalizing short-video search, where $\text{PR}^2$ stands for the Personalized Retrieval and Ranking augmented search system. Specifically, $\text{PR}^2$ leverages query-relevant collaborative filtering and personalized dense retrieval to extract relevant and individually tailored content from a large-scale video corpus. Furthermore, it utilizes the QIN (Query-Dominate User Interest Network) ranking model, to effectively harness user long-term preferences and real-time behaviors, and efficiently learn from user various implicit feedback through a multi-task learning framework. By deploying the $\text{PR}^2$ in production system, we have achieved the most remarkable user engagement improvements in recent years: a 10.2% increase in CTR@10, a notable 20% surge in video watch time, and a 1.6% uplift of search DAU. We believe the practical insights presented in this work are valuable especially for building and improving personalized search systems for the short video platforms.

Dense features, customized for different business scenarios, are essential in short video classification. However, their complexity, specific adaptation requirements, and high computational costs make them resource-intensive and less accessible during online inference. Consequently, these dense features are categorized as `Privileged Dense Features'.Meanwhile, end-to-end multi-modal models have shown promising results in numerous computer vision tasks. In industrial applications, prioritizing end-to-end multi-modal features, can enhance efficiency but often leads to the loss of valuable information from historical privileged dense features. To integrate both features while maintaining efficiency and manageable resource costs, we present Confidence-aware Privileged Feature Distillation (CPFD), which empowers features of an end-to-end multi-modal model by adaptively distilling privileged features during training. Unlike existing privileged feature distillation (PFD) methods, which apply uniform weights to all instances during distillation, potentially causing unstable performance across different business scenarios and a notable performance gap between teacher model (Dense Feature enhanced multimodal-model DF-X-VLM) and student model (multimodal-model only X-VLM), our CPFD leverages confidence scores derived from the teacher model to adaptively mitigate the performance variance with the student model. We conducted extensive offline experiments on five diverse tasks demonstrating that CPFD improves the video classification F1 score by 6.76% compared with end-to-end multimodal-model (X-VLM) and by 2.31% with vanilla PFD on-average. And it reduces the performance gap by 84.6% and achieves results comparable to teacher model DF-X-VLM. The effectiveness of CPFD is further substantiated by online experiments, and our framework has been deployed in production systems for over a dozen models., Comment: Camera ready for CIKM 2024

Personality analysis from online short videos has gained prominence due to its applications in personalized recommendation systems, sentiment analysis, and human-computer interaction. Traditional assessment methods, such as questionnaires based on the Big Five Personality Framework, are limited by self-report biases and are impractical for large-scale or real-time analysis. Leveraging the rich, multi-modal data present in short videos offers a promising alternative for more accurate personality inference. However, integrating these diverse and asynchronous modalities poses significant challenges, particularly in aligning time-varying data and ensuring models generalize well to new domains with limited labeled data. In this paper, we propose a novel multi-modal personality analysis framework that addresses these challenges by synchronizing and integrating features from multiple modalities and enhancing model generalization through domain adaptation. We introduce a timestamp-based modality alignment mechanism that synchronizes data based on spoken word timestamps, ensuring accurate correspondence across modalities and facilitating effective feature integration. To capture temporal dependencies and inter-modal interactions, we employ Bidirectional Long Short-Term Memory networks and self-attention mechanisms, allowing the model to focus on the most informative features for personality prediction. Furthermore, we develop a gradient-based domain adaptation method that transfers knowledge from multiple source domains to improve performance in target domains with scarce labeled data. Extensive experiments on real-world datasets demonstrate that our framework significantly outperforms existing methods in personality prediction tasks, highlighting its effectiveness in capturing complex behavioral cues and robustness in adapting to new domains.

Short-video recommender systems often exhibit a biased preference to recently released videos. However, not all videos become outdated; certain classic videos can still attract user's attention. Such bias along temporal dimension can be further aggravated by the matching model between users and videos, because the model learns from preexisting interactions. From real data, we observe that different videos have varying sensitivities to recency in attracting users' attention. Our analysis, based on a causal graph modeling short-video recommendation, suggests that the release interval serves as a confounder, establishing a backdoor path between users and videos. To address this confounding effect, we propose a model-agnostic causal architecture called Learning to Deconfound the Release Interval Bias (LDRI). LDRI enables jointly learning of the matching model and the video recency sensitivity perceptron. In the inference stage, we apply a backdoor adjustment, effectively blocking the backdoor path by intervening on each video. Extensive experiments on two benchmarks demonstrate that LDRI consistently outperforms backbone models and exhibits superior performance against state-of-the-art models. Additional comprehensive analyses confirm the deconfounding capability of LDRI.

As short-form video-sharing platforms become a significant channel for news consumption, fake news in short videos has emerged as a serious threat in the online information ecosystem, making developing detection methods for this new scenario an urgent need. Compared with that in text and image formats, fake news on short video platforms contains rich but heterogeneous information in various modalities, posing a challenge to effective feature utilization. Unlike existing works mostly focusing on analyzing what is presented, we introduce a novel perspective that considers how it might be created. Through the lens of the creative process behind news video production, our empirical analysis uncovers the unique characteristics of fake news videos in material selection and editing. Based on the obtained insights, we design FakingRecipe, a creative process-aware model for detecting fake news short videos. It captures the fake news preferences in material selection from sentimental and semantic aspects and considers the traits of material editing from spatial and temporal aspects. To improve evaluation comprehensiveness, we first construct FakeTT, an English dataset for this task, and conduct experiments on both FakeTT and the existing Chinese FakeSV dataset. The results show FakingRecipe's superiority in detecting fake news on short video platforms., Comment: Will appear at ACM Multimedia 2024 (MM 2024), 13 pages, 15 figures

Accurately predicting watch time is crucial for optimizing recommendations and user experience in short video platforms. However, existing methods that estimate a single average watch time often fail to capture the inherent uncertainty and diversity in user engagement patterns. In this paper, we propose the Conditional Quantile Estimation (CQE) framework to model the entire conditional distribution of watch time. Using quantile regression, CQE characterizes the complex watch-time distribution for each user-video pair, providing a flexible and comprehensive approach to understanding user behavior. We further design multiple strategies to combine the quantile estimates, adapting to different recommendation scenarios and user preferences. Extensive offline experiments and online A/B tests demonstrate the superiority of CQE in watch time prediction and user engagement modeling. In particular, the online deployment of CQE in KuaiShow has led to significant improvements in key evaluation metrics, including active days, active users, engagement duration, and video view counts. These results highlight the practical impact of our proposed approach in enhancing the user experience and overall performance of the short video recommendation system. The code will be released after publication., Comment: 8 pages, 5 figures, 5 tables

The surge in popularity of short-form video content, particularly through platforms like TikTok and Instagram, has led to an exponential increase in data traffic, presenting significant challenges in network resource management. Traditional unicast streaming methods, while straightforward, are inefficient in scenarios where videos need to be delivered to a large number of users simultaneously. Multicast streaming, which sends a single stream to multiple users, can drastically reduce the required bandwidth, yet it introduces complexities in resource allocation, especially in wireless environments where bandwidth is limited and user demands are heterogeneous. This paper introduces a novel multicast resource management framework tailored for the efficient distribution of short-form video content. The proposed framework dynamically optimizes resource allocation to enhance Quality of Service (QoS) and Quality of Experience (QoE) for multiple users, balancing the trade-offs between cost, efficiency, and user satisfaction. We implement a series of optimization algorithms that account for diverse network conditions and user requirements, ensuring optimal service delivery across varying network topologies. Experimental results demonstrate that our framework can effectively reduce bandwidth usage and decrease video startup delay compared to traditional multicast approaches, significantly improving overall user satisfaction. This study not only advances the understanding of multicast streaming dynamics but also provides practical insights into scalable and efficient video distribution strategies in congested network environments.

Recommender selects and presents top-K items to the user at each online request, and a recommendation session consists of several sequential requests. Formulating a recommendation session as a Markov decision process and solving it by reinforcement learning (RL) framework has attracted increasing attention from both academic and industry communities. In this paper, we propose a RL-based industrial short-video recommender ranking framework, which models and maximizes user watch-time in an environment of user multi-aspect preferences by a collaborative multi-agent formulization. Moreover, our proposed framework adopts a model-based learning approach to alleviate the sample selection bias which is a crucial but intractable problem in industrial recommender system. Extensive offline evaluations and live experiments confirm the effectiveness of our proposed method over alternatives. Our proposed approach has been deployed in our real large-scale short-video sharing platform, successfully serving over hundreds of millions users.

In recent years, short video platforms have gained widespread popularity, making the quality of video recommendations crucial for retaining users. Existing recommendation systems primarily rely on behavioral data, which faces limitations when inferring user preferences due to issues such as data sparsity and noise from accidental interactions or personal habits. To address these challenges and provide a more comprehensive understanding of user affective experience and cognitive activity, we propose EEG-SVRec, the first EEG dataset with User Multidimensional Affective Engagement Labels in Short Video Recommendation. The study involves 30 participants and collects 3,657 interactions, offering a rich dataset that can be used for a deeper exploration of user preference and cognitive activity. By incorporating selfassessment techniques and real-time, low-cost EEG signals, we offer a more detailed understanding user affective experiences (valence, arousal, immersion, interest, visual and auditory) and the cognitive mechanisms behind their behavior. We establish benchmarks for rating prediction by the recommendation algorithm, showing significant improvement with the inclusion of EEG signals. Furthermore, we demonstrate the potential of this dataset in gaining insights into the affective experience and cognitive activity behind user behaviors in recommender systems. This work presents a novel perspective for enhancing short video recommendation by leveraging the rich information contained in EEG signals and multidimensional affective engagement scores, paving the way for future research in short video recommendation systems.

The short video-sharing services that allow users to post 10-30 second videos (e.g., YouTube Shorts and TikTok) have attracted a lot of attention in recent years. However, conventional video copy detection (VCD) methods mainly focus on general video-sharing services (e.g., YouTube and Bilibili), and the effects of short video-sharing services on video copy detection are still unclear. Considering that illegally copied videos in short video-sharing services have service-distinctive characteristics, especially in those time lengths, the pros and cons of VCD in those services are required to be analyzed. In this paper, we examine the effects of short video-sharing services on VCD by constructing a dataset that has short video-sharing service characteristics. Our novel dataset is automatically constructed from the publicly available dataset to have reference videos and fixed short-time-length query videos, and such automation procedures assure the reproducibility and data privacy preservation of this paper. From the experimental results focusing on segment-level and video-level situations, we can see that three effects: "Segment-level VCD in short video-sharing services is more difficult than those in general video-sharing services", "Video-level VCD in short video-sharing services is easier than those in general video-sharing services", "The video alignment component mainly suppress the detection performance in short video-sharing services".

Filter bubbles have been studied extensively within the context of online content platforms due to their potential to cause undesirable outcomes such as user dissatisfaction or polarization. With the rise of short-video platforms, the filter bubble has been given extra attention because these platforms rely on an unprecedented use of the recommender system to provide relevant content. In our work, we investigate the deep filter bubble, which refers to the user being exposed to narrow content within their broad interests. We accomplish this using one-year interaction data from a top short-video platform in China, which includes hierarchical data with three levels of categories for each video. We formalize our definition of a "deep" filter bubble within this context, and then explore various correlations within the data: first understanding the evolution of the deep filter bubble over time, and later revealing some of the factors that give rise to this phenomenon, such as specific categories, user demographics, and feedback type. We observe that while the overall proportion of users in a filter bubble remains largely constant over time, the depth composition of their filter bubble changes. In addition, we find that some demographic groups that have a higher likelihood of seeing narrower content and implicit feedback signals can lead to less bubble formation. Finally, we propose some ways in which recommender systems can be designed to reduce the risk of a user getting caught in a bubble., Comment: accepted to WWW 2024

Investigating the increasingly popular domain of short video consumption, this study focuses on the impact of Opinion Polarization (OP), a significant factor in the digital landscape influencing public opinions and social interactions. We analyze OP's effect on viewers' perceptions and behaviors, finding that traditional feedback metrics like likes and watch time fail to fully capture and measure OP. Addressing this gap, our research utilizes Electroencephalogram (EEG) signals to introduce a novel, non-invasive approach for evaluating neural responses to OP, affecting perception and cognition. Empirical analysis reveals OP's considerable impact on viewers' emotions, evidenced by changes in brain activity. Our findings also highlight the potential of EEG data in predicting exposure to polarized short video content, offering a new perspective on the dynamics of short video consumption and a unique method for quantifying OP's effects., Comment: 9 pages, 8 figures

In this paper, we propose a novel efficient digital twin (DT) data processing scheme to reduce service latency for multicast short video streaming. Particularly, DT is constructed to emulate and analyze user status for multicast group update and swipe feature abstraction. Then, a precise measurement model of DT data processing is developed to characterize the relationship among DT model size, user dynamics, and user clustering accuracy. A service latency model, consisting of DT data processing delay, video transcoding delay, and multicast transmission delay, is constructed by incorporating the impact of user clustering accuracy. Finally, a joint optimization problem of DT model size selection and bandwidth allocation is formulated to minimize the service latency. To efficiently solve this problem, a diffusion-based resource management algorithm is proposed, which utilizes the denoising technique to improve the action-generation process in the deep reinforcement learning algorithm. Simulation results based on the real-world dataset demonstrate that the proposed DT data processing scheme outperforms benchmark schemes in terms of service latency., Comment: 6 pages, 6 figures, submitted to ICCC 2024

In recent years, the global unemployment rate has remained persistently high. Compounding this issue, the ageing population in China often encounters additional challenges in finding employment due to prevalent age discrimination in daily life. However, with the advent of social media, there has been a rise in the popularity of short videos and live-streams for recruiting ageing workers. To better understand the motivations of ageing job seekers to engage with these video-based recruitment methods and to explore the extent to which such platforms can empower them, we conducted an interview-based study with ageing job seekers who have had exposure to these short recruitment videos and live-streaming channels. Our findings reveal that these platforms can provide a job-seeking choice that is particularly friendly to ageing job seekers, effectively improving their disadvantaged situation., Comment: 14 pages, 3 figures; Accepted to ACM CHI 2024. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI'24)

While short videos bring a lot of information and happiness to users, they also occupy users time and short videos gradually change peoples living habits. This paper studies the negative effects and negative emotions of users caused by using short video platforms, as well as the users intention to continue using the short video platform when they have negative emotions. Therefore, this study uses flow theory and illusion of control theory to construct a research hypothesis model and preliminarily confirms six influencing factors, and uses sequential mixed research method to conduct quantitative and qualitative research. The results show that users use of short video platforms will have negative emotions and negative emotions will affect users intention to continue to use short video platforms. This study expands the breadth and depth of research on short videos and enriches the research of negative emotions on the intention to continue using human computer interaction software. Additionally, illusion of control theory is introduced into the field of human computer interaction for the first time, which enriches the application scenarios of control illusion theory., Comment: Electronic Commerce Research and Applications (2023)

Vision-Language Models pre-trained on large-scale image-text datasets have shown superior performance in downstream tasks such as image retrieval. Most of the images for pre-training are presented in the form of open domain common-sense visual elements. Differently, video covers in short video search scenarios are presented as user-originated contents that provide important visual summaries of videos. In addition, a portion of the video covers come with manually designed cover texts that provide semantic complements. In order to fill in the gaps in short video cover data, we establish the first large-scale cover-text benchmark for Chinese short video search scenarios. Specifically, we release two large-scale datasets CBVS-5M/10M to provide short video covers, and the manual fine-labeling dataset CBVS-20K to provide real user queries, which serves as an image-text benchmark test in the Chinese short video search field. To integrate the semantics of cover text in the case of modality missing, we propose UniCLIP where cover texts play a guiding role during training, however are not relied upon by inference. Extensive evaluation on CBVS-20K demonstrates the excellent performance of our proposal. UniCLIP has been deployed to Tencent's online video search systems with hundreds of millions of visits and achieved significant gains. The dataset and code are available at https://github.com/QQBrowserVideoSearch/CBVS-UniCLIP.

Multicast short video streaming can enhance bandwidth utilization by enabling simultaneous video transmission to multiple users over shared wireless channels. The existing network management schemes mainly rely on the sequential buffering principle and general quality of experience (QoE) model, which may deteriorate QoE when users' swipe behaviors exhibit distinct spatiotemporal variation. In this paper, we propose a digital twin (DT)-based network management scheme to enhance QoE. Firstly, user status emulated by the DT is utilized to estimate the transmission capabilities and watching probability distributions of sub-multicast groups (SMGs) for an adaptive segment buffering. The SMGs' buffers are aligned to the unique virtual buffers managed by the DT for a fine-grained buffer update. Then, a multicast QoE model consisting of rebuffering time, video quality, and quality variation is developed, by considering the mutual influence of segment buffering among SMGs. Finally, a joint optimization problem of segment version selection and slot division is formulated to maximize QoE. To efficiently solve the problem, a data-model-driven algorithm is proposed by integrating a convex optimization method and a deep reinforcement learning algorithm. Simulation results based on the real-world dataset demonstrate that the proposed DT-based network management scheme outperforms benchmark schemes in terms of QoE improvement., Comment: 13 pages, 12 figures

Short video recommendations often face limitations due to the quality of user feedback, which may not accurately depict user interests. To tackle this challenge, a new task has emerged: generating more dependable labels from original feedback. Existing label generation methods rely on manual rules, demanding substantial human effort and potentially misaligning with the desired objectives of the platform. To transcend these constraints, we introduce LabelCraft, a novel automated label generation method explicitly optimizing pivotal operational metrics for platform success. By formulating label generation as a higher-level optimization problem above recommender model optimization, LabelCraft introduces a trainable labeling model for automatic label mechanism modeling. Through meta-learning techniques, LabelCraft effectively addresses the bi-level optimization hurdle posed by the recommender and labeling models, enabling the automatic acquisition of intricate label generation mechanisms.Extensive experiments on real-world datasets corroborate LabelCraft's excellence across varied operational metrics, encompassing usage time, user engagement, and retention. Codes are available at https://github.com/baiyimeng/LabelCraft., Comment: Accepted by WSDM'24

Practitioners who wish to build real-world applications that rely on ranking models, need to decide which modelling paradigm to follow. This is not an easy choice to make, as the research literature on this topic has been shifting in recent years. In particular, whilst Gradient Boosted Decision Trees (GBDTs) have reigned supreme for more than a decade, the flexibility of neural networks has allowed them to catch up, and recent works report accuracy metrics that are on par. Nevertheless, practical systems require considerations beyond mere accuracy metrics to decide on a modelling approach. This work describes our experiences in balancing some of the trade-offs that arise, presenting a case study on a short-video recommendation application. We highlight (1) neural networks' ability to handle large training data size, user- and item-embeddings allows for more accurate models than GBDTs in this setting, and (2) because GBDTs are less reliant on specialised hardware, they can provide an equally accurate model at a lower cost. We believe these findings are of relevance to researchers in both academia and industry, and hope they can inspire practitioners who need to make similar modelling choices in the future., Comment: Appearing in the Industry Track Proceedings of the Forum for Information Retrieval Evaluation (FIRE '23)