Back to Search
Author profile
Affiliations
Documents
[AHG11] Additional Information on Stable Float Method for Neural Network Inference on GPU devices
EE1-5: operational bit-exact reproducibility
EE1-4.4: Integrating End-to-End Learned Intra-Frame Codec with Conventional Codec
EE1-4.3: Integrating End-to-End Learned Intra-Frame Codec with Conventional Codec
EE1-4.2: Integrating End-to-End Learned Intra-Frame Codec with Conventional Codec
EE1-4.1: Integrating End-to-End Learned Intra-Frame Codec with Conventional Codec
EE2-2.1a/b/c: Modified GPM partition mode
Non-EE2: On GPM mode
[AHG11] Stable float convolution for neural network inference
[AHG11] A Hybrid Framework Integrating End-to-End Learned Intra-Frame Codec with Conventional Codec
EE1-6.2: Integrating End-to-End Learned Intra-Frame Codec with Conventional Codec
EE1-6.1: Integrating End-to-End Learned Intra-Frame Codec with Conventional Codec
[AHG17] Suggestions on Draft CfP, CTCs and complexity reporting
Crosscheck of JVET-AO0141 (EE2-4.4: Improvement on picture-level inheritance mode in ALF-CCCM)
EE2-4.3: Additional candidates for merge mode in ALF-CCCM
Non-EE2: Additional candidates for merge mode in ALF-CCCM
[AHG11] A Hybrid Framework Integrating End-to-End Learned Intra-Frame Codec with Conventional Codec
[AHG11/AHG14] Comparison of Multi-Layer and Single-Layer Interfaces for Hybrid End-to-End Video Coding Frameworks
EE1-related: Automated environment information collection
AHG11: A Hybrid Framework Integrating End-to-End Learned Image Codec with Conventional Codec
Non-EE2: Enhanced CCP merge mode with BVG-CCCM model
AHG9: EOI SEI message with luma range adaptation for machine analysis
[AHG11] A Hybrid Framework Integrating End-to-End Learned Image Codec with Conventional Codec
EE1-1.1: Multiscale blocks in LOP5 and VLOP3 filters
AHG9/AHG8: Showcase for Packed regions information SEI
AHG11/AHG14: Content-adaptive LOP4 filter
[AHG11] A Hybrid Framework Integrating End-to-End Learned Image Codec with Conventional Codec
EE1-1.3: Multiscale blocks in LOP4 and VLOP3 filters
EE2-2.4: GPM extension
Crosscheck of JVET-AK0094 (AHG8: On combination of adaptive temporal resampling, pre-processing, post-processing and ROI-based adaptive QP algorithm for machine vision)
AHG8: Add Packed regions info SEI to TR on coding video for machine consumption
Non-EE2: GPM extension
Crosscheck of JVET-AJ0181 (AHG8: On combination of pre-processing, post-processing and ROI-based adaptive QP algorithm for machine vision)
Crosscheck of JVET-AJ0178 (AHG8: Lightweight post-processing algorithm for machine consumption)
EE1-1.5: Multiscale blocks in LOP3 and VLOP2 filter
Crosscheck of JVET-AI0196(AHG8: On combined pre- and post-processing and ROI-based adaptive QP for machine vision)
AHG11: Deep Reference Frame Generation for VVC Inter Coding
EE1-1.4: Content-adaptive VLOP-filter
AhG11: LOP3 filter with multiscale blocks
AHG8/AHG9: Indication of NNPFs and processing chains for human viewing and/or machine consumption
AhG11: Content-adaptive LOP3 filter
AHG8: Reduced residual encoding in VVC for machine consumption
AHG8: Semantic segmentation task for VCM with PandaSet
AHG8: Multi-layer VVC for hybrid machine-human consumption
Crosscheck of JVET-AH0157(AHG8: On combined pre-processing and post-processing for machine vision)
EE1-1.4: Content-adaptive loop-filter
AHG8/AHG9: Indication of NNPFs and processing chains for machine consumption
AHG9: Region packing information SEI
AHG9: On the encoder optimization information SEI message
AHG8: Reduced residual encoding in VVC for machine consumption
Crosscheck of AG0212 (AHG8: A post-processing algorithm for machine consumption)
AHG8: Multi-layer VVC for hybrid machine-human consumption
EE1-2.2: Content-adaptive LOP filter
AHG1/AHG2/AHG8: On project management related to the encoder optimization information SEI message
AHG9: On the generative face video SEI message
AHG9: Temporal extrapolation purpose for the neural-network post-filter characteristics SEI message
AHG9: Usage of the neural-network post-filter characteristics SEI message to define the generator NN of the generative face video SEI message
Crosscheck of JVET-AF0122 (AhG10: Lagrange multiplier optimization for chroma ALF and CCALF)
EE1-1.2.2: Content-adaptive LOP filter
Crosscheck of JVET-AE0123 (AHG10: Lagrange multiplier optimization for chroma ALF and CCALF)
AHG11: Content-adaptive neural network loop-filter
AHG8: Crosscheck of JVET-AE0107
EE2-2.9: Extended search areas for IntraTMP mode
AHG8/AHG9: Signalling encoder preprocessing and human / machine viewing indications
Crosscheck of JVET-AD0163 (AHG11: Updating NNPFC and NNPFA SEI messages for the NNPF)
EE2-1.20i/j: Combination of IntraTMP tests
EE2-related: Combination of JVET-AD0084, JVET-AD0117 and JVET-AD0214
EE2-1.20n: Combination Test of Test 1.20f + Test 1.14c
EE2-1.14c combination test of EE2-1.14a and EE2-1.14b
EE1-1.5: Ablation Study and Minor Improvements on RTNN
AHG8/AHG9: Indications related to suboptimal user viewing
AHG11: Neural network loop filter
EE2-1.20k: Combination of Test 1.12 and Test 1.14c
AHG9: NNPFC SEI extension mechanism to enable usages beyond user viewing
[EE1-related] RTNN: An In-loop Filter Based on Resblock and Transformer
EE1-1.11: Content-adaptive post-filter
Crosscheck of JVET-AC0060 (EE2-3.4: BVP candidates clustering and BVD sign derivation for Reconstruction-Reordered IBC mode)
AHG9/AHG15: On bitstreams that are potentially suboptimal for user viewing
AHG9/AHG15: On the NNPFC SEI message for machine analysis
EE1-1.1: Content-adaptive post-filter with SADL inference and signalling of NN post-filter characteristics and activation SEI messages
EE1-1.3 related: Lightweight and Efficient CNN In-loop Filter
EE1-1.3: CNN Based In-Loop Filter with WCDANN
EE1-1.7: Content-adaptive post-filter based on SADL inference
[EE1-related] Lighter WCDANN: CNN Based In-Loop Filters
AHG10: Report of temporal layer dependent deblocking filter setting for HM
AHG11: Content-adaptive neural network post-filter
EE1-1.5: Test on NN-based filter as proposed in JVET-Y0052
AHG10: Report of Deblocking filter setting for VTM
Crosscheck of JVET-Y0118 (AHG10: On Temporal-Layer-Based ChromaQP Coding)
AHG11: CNN post-processing filter based on depthwise separable convolution and attention mechanism
AHG11: Content-adaptive post-processing filter
AhG10: Report of Teleconference on Viewing Session Preparation for Deblocking
AHG10: Deblocking filter setting for VTM
AHG11: MPEG NNR compressed bias update for the CNN based post-filter of EE1-1.1
EE1-1.1: Content-adaptive neural network post-processing filter
AHG11: Content-adaptive neural network post-processing filter
AHG11: Content-adaptive neural network post-processing filter
AHG15: On Chroma Quantization Matrix Signalling
AHG15: Improvement for Quantization Matrix Signaling
Interaction between ACT and cross-component coding tools
AHG15: Clean up for signaling quantization matrix
SW for technology proposal by Samsung, Huawei, GoPro, and HiSilicon – mobile application scenario (JVET-J0024)
Surveillance class and CTC for video coding development
Description of SDR, HDR and 360° video coding technology proposal by Huawei, GoPro, HiSilicon, and Samsung – general application scenario
Description of SDR, HDR and 360° video coding technology proposal by Samsung, Huawei, GoPro, and HiSilicon – mobile application scenario
Cross-check of JVET-E0039 on a unified condition for affine merge and affine inter mode
Perceptual Quality Assessment Metric MS-SSIM
Surveillance sequences for video coding development
Cross-check of JVET-C0025: Simplification of motion compensation filter for affine inter prediction
Suggested 1080P Test Sequences Downsampled from 4K Sequences
Performance analysis of affine inter prediction in JEM1.0
Cross-check of Simplification of affine flag signaling condition (JVET-E0039)
Withdrawn
AHG10/AHG12: Clean-Slate NextSoftware2 implementation without future Video Coding Tools
AHG9: Implementation and showcase of the luma adaptation extension of the EOI SEI message