0 views collected around this technical thread.
Tencent’s TVQA‑C video quality assessment algorithm clinched first place in the ECCV 2024 AIM Workshop compression video quality track, showcasing a novel model architecture, group‑aware training strategy, and specialized loss functions that will soon power Tencent Cloud’s media processing services.
The CVPR NTIRE 2024 short-form video quality assessment competition introduced the KVQ dataset, attracted over 200 teams, evaluated submissions using SROCC and PLCC metrics, and highlighted the winning approaches of SJTU MMLab, IH‑VQA, and TVQE, showcasing advances in AI‑driven video quality evaluation.
Kwai (Kuaishou) has eight papers accepted at CVPR 2024 covering multi‑dimensional human preference for text‑to‑image generation, short‑video quality assessment, efficient video quality assessment, compressed video enhancement, conditional unsigned distance fields, universal cross‑domain retrieval, perception‑oriented frame interpolation, and test‑time energy adaptation.
Xiaohongshu’s audio‑video architecture team secured second place in the RAIM challenge and first in the S‑UGC VQA challenge at CVPR NTIRE 2024 by improving generative image restoration with SUPIR, DeSRA and a Fusion model, and enhancing video quality assessment using LIQE, Q‑Align and FAST‑VQA, then deploying these methods for live‑stream denoising, intelligent transcoding and cloud‑based super‑resolution, achieving high PLCC/SROCC scores and up to 33 % bandwidth savings.
Kuaishou invites attendees to its CVPR 2024 presence in Seattle, featuring an elite dinner, booth talks, tech talks, and a showcase of eight accepted papers covering video quality assessment, image generation, and multimodal AI, with detailed schedules, authors, and presentation locations, plus recruitment opportunities.
The CVPR NTIRE 2024 workshop hosts the first short‑video quality assessment competition, introducing the KVQ dataset of 4,200 videos across nine scenes, providing training/validation data, a baseline 3D Swin‑Transformer model, detailed competition rules, rewards, and organizer contacts.
This article reviews the latest research from Alibaba DAMO Academy on real-world image quality problems, covering spatial, temporal, and color enhancement methods, advanced quality assessment metrics, multimodal diffusion models, and future directions toward large‑model integration and lightweight deployment.
This article presents concise English summaries of nine Kuaishou research papers accepted at ACM MM 2023, covering topics such as no‑reference video quality assessment, adaptive video quality models, blind image super‑resolution, audio‑visual‑language transfer learning, motion‑aware video diffusion, large‑scale e‑commerce retrieval, and interactive segmentation.
BILIVQA is Bilibili’s deep‑learning, no‑reference video quality assessment system that trains on a proprietary 5,000‑video UGC dataset, extracts spatial and temporal features via MobileNet‑V2 and X3D, uses mixed‑dataset regression for strong generalization, and deploys a GPU‑optimized TensorRT pipeline with percentile‑based scoring for reliable quality monitoring and downstream applications.
Alibaba’s Taobao VQA team won the CVPR NTIRE 2023 Video Enhancement Challenge by introducing MD‑VQA, a multi‑dimensional no‑reference video quality model that combines a Swin‑Transformer‑V2 spatial backbone, a pre‑trained SlowFast motion encoder, and a convolutional fusion module, pre‑trained on LSVQ, fine‑tuned on NTIRE data, and augmented spatio‑temporally, achieving state‑of‑the‑art SROCC and PLCC scores and now powering quality monitoring on Alibaba’s live‑streaming and short‑video services.
MD‑VQA is a no‑reference video quality assessment model that combines semantic cues from EfficientNetV2, handcrafted distortion metrics, and motion information from ResNet3D‑18 to predict absolute quality of user‑generated live videos, trained on the large TaoLive dataset and achieving state‑of‑the‑art SRCC and PLCC results that are already deployed for real‑time monitoring on Taobao’s streaming platform.
Bilibili’s comprehensive video‑quality framework merges ITU‑R BT.500 subjective MOS testing with objective metrics such as PSNR, SSIM, VMAF and NIQE—including HDR10 and HLG assessment—through a full capture‑to‑encoding workflow, addressing alignment and content‑specific challenges and delivering measurable QoE and speed gains across its platforms.
TDQA is a no‑reference, deep‑learning video quality assessment algorithm designed for live‑streaming, built on a large subjectively annotated dataset and an end‑to‑end architecture with fine‑tuned backbones, achieving state‑of‑the‑art accuracy and sub‑second inference for real‑time quality monitoring and pipeline optimization.