Related papers: Comyco: Quality-Aware Adaptive Video Streaming via…
Sampling strategies have been widely applied in many recommendation systems to accelerate model learning from implicit feedback data. A typical strategy is to draw negative instances with uniform distribution, which however will severely…
Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better…
Video streaming today accounts for up to 55\% of mobile traffic. In this paper, we explore streaming videos encoded using Scalable Video Coding scheme (SVC) over highly variable bandwidth conditions such as cellular networks. SVC's unique…
Clustering bandits have gained significant attention in recommender systems by leveraging collaborative information from neighboring users to better capture target user preferences. However, these methods often lack a clear definition of…
Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance. Worse still, the conventional static…
In this paper, we propose a novel algorithm for video rate adaptation in HTTP Adaptive Streaming (HAS), based on online learning. The proposed algorithm, named Learn2Adapt (L2A), is shown to provide a robust rate adaptation strategy which,…
Video compression plays a crucial role in video streaming and classification systems by maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this paper, we conduct the first systematic study for adversarial…
In video coding, compressed videos with certain and constant quality can ensure quality of experience (QoE). To this end, we propose in this paper a novel PID-based quality control (PQC) method for video coding. Specifically, a formulation…
In this paper we propose a generative adversarial network (GAN) framework to enhance the perceptual quality of compressed videos. Our framework includes attention and adaptation to different quantization parameters (QPs) in a single model.…
Conventional video encoders typically employ a fixed chroma subsampling format, such as YUV420, which may not optimally reflect variations in chroma detail across different types of content. This can lead to suboptimal chroma quality and…
End-to-end learned video compression has achieved strong rate-distortion performance, but rate control remains underexplored, especially in target-bitrate-driven and budget-constrained scenarios. Existing methods mainly rely on explicit…
Imitation learning is a promising approach for training autonomous vehicles (AV) to navigate complex traffic environments by mimicking expert driver behaviors. While existing imitation learning frameworks focus on leveraging expert…
User-perceived quality-of-experience (QoE) is critical in internet video delivery systems. Extensive prior work has studied the design of client-side bitrate adaptation algorithms to maximize single-player QoE. However, multiplayer QoE…
In recent years, the field of learned video compression has witnessed rapid advancement, exemplified by the latest neural video codecs DCVC-DC that has outperformed the upcoming next-generation codec ECM in terms of compression ratio.…
HTTP based adaptive video streaming has become a popular choice of streaming due to the reliable transmission and the flexibility offered to adapt to varying network conditions. However, due to rate adaptation in adaptive streaming, the…
Trajectory Optimization (TO) and Reinforcement Learning (RL) offer complementary strengths for solving optimal control problems. TO efficiently computes locally optimal solutions but can struggle with non-convexity, while RL is more robust…
Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…
Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which…
Humans can efficiently extract knowledge and learn skills from the videos within only a few trials and errors. However, it poses a big challenge to replicate this learning process for autonomous agents, due to the complexity of visual…
Adam is a widely used optimizer in neural network training due to its adaptive learning rate. However, because different data samples influence model updates to varying degrees, treating them equally can lead to inefficient convergence. To…