[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83306-en":3,"doc-seo-83306-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},83306,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Towards Robust Semantic Video Transmission over Block Erasure Channels","This paper investigates semantic-aware neural joint source-channel coding (JSCC) for robust video transmission over block erasure channels. A neural video compression framework is developed with spatial-domain and feature-domain designs. Spatial-domain partitioning enables localized erasure handling using uniform and two-level semantic-guided non-uniform strategies, while feature-domain partitioning recovers missing latent features via semantic cues while preserving spatial consistency. Experiments compare reconstruction quality under varying erasure probabilities and reveal trade-offs between spatial continuity and semantic redundancy.","Towards Robust Semantic Video Transmission over  \nBlock Erasure Channels  \nNargis Fayaz 1 , Homa Esfahanizadeh2 , Matin Mortaheb2 , Jinfeng Du2 , Harish Viswanathan2  \n1 Nokia Bell Labs, India 2 Nokia Bell Labs, Murray Hill, New Jersey, USA  \n[eez218533@ee.iitd.ac.in](eez218533@ee.iitd.ac.in), {homa.esfahanizadeh, matin.mortaheb, jinfeng.du, [harish.viswanathan](harish.viswanathan}@nokia-bell-labs.com)[}](harish.viswanathan}@nokia-bell-labs.com)[@nokia-bell-labs.com](harish.viswanathan}@nokia-bell-labs.com)  \narXiv :2607 .07823v1 [ ee ss .IV] 8 Jul 2026  \nAbstract—This paper investigates semantic-aware neural joint source-channel coding (JSCC) for robust video transmission over block erasure channels. We propose a neural video compression framework exploring both spatial-domain and feature-domain designs. In the spatial domain, video frames are partitioned into blocks, enabling localized erasure handling and fine-grained robustness control via uniform erasure and two-level, semanticguided non-uniform erasure strategies. In the feature domain, latent features are partitioned, enabling missing features to be semantically recovered while maintaining overall spatial consistency. Comprehensive experiments quantify reconstruction quality under varying uniform and non-uniform erasure probabilities. Our results show that spatial-domain JSCC excels at handling random localized losses, whereas feature-domain JSCC provides superior robustness to distributed erasures and maintains fidelity under low-loss scenarios. The analysis highlights the trade-offs between spatial continuity and semantic redundancy, offering insights for designing robust, task-aware video communication systems.  \nIndex Terms—Block erasure channels, joint source-channel coding, robust video transmission, semantic communication, video compression.  \nI. INTRODUCTION  \nVideo dominates global internet traffic, accounting for over 80% of downstream data, driven by applications such as video-on-demand, conferencing, and immersive media. The increasing adoption of ultra-high-definition formats (4K/8K), high frame rates, and high dynamic range substantially raises bitrate requirements, making efficient compression essential for scalable storage and transmission. Traditional codecs such as H.264/AVC [1] and H.265/HEVC [2] employ hybrid blockbased frameworks that integrate intra and inter prediction, transform coding, quantization, and entropy coding. End-toend neural network based video compression, using autoencoders, variational autoencoders, or recurrent and transformer architectures, jointly optimizes spatiotemporal feature extraction, quantization, and entropy coding, often surpassing HEVC in rate–distortion performance [3]–[5] .  \nBeyond compression, reliable video transmission over practical wireless channels requires robustness to noise, fading, and packet loss. Classical systems address compression and error correction separately, following the Shannon separation principle, which can be inefficient in lossy environments and practical code lengths. Neural joint source channel coding (JSCC) overcomes this limitation by directly mapping source video to channel symbols and reconstructing it at the receiver, enabling graceful quality degradation over a noisy channel  \n[6], [7] . This paradigm is particularly advantageous for realtime applications such as video conferencing, telemedicine, and UAV streaming, where retransmission is often impractical or ineffective due to low-delay requirements.  \nRecently, semantic video communication has emerged as a complementary paradigm. Applications include video conferencing [8], autonomous driving [9], and general video understanding using rate-distortion autoencoders [10] . Integrating semantic awareness with NN-based JSCC enables a unified framework that jointly optimizes compression, semantic relevance, and channel robustness, making it well suited for low-latency, resource-constrained, and lossy communication environments [11] .  ","cbCaigOL88RA59Pa","https://ap.wps.com/l/cbCaigOL88RA59Pa","pdf",44773022,1,5,"English","en",105,"# Introduction\n# System Model and Method\n## Semantic-Aware Neural Joint Source–Channel Coding\n## Video Transmission Framework","[{\"question\":\"What is the main goal of the paper?\",\"answer\":\"The paper aims to make neural video transmission robust to block erasures by combining semantic awareness with joint source-channel coding.\"},{\"question\":\"How does the spatial-domain approach handle block erasures?\",\"answer\":\"It partitions video frames into blocks and applies uniform erasure handling as well as two-level semantic-guided non-uniform erasure strategies to control robustness at finer granularity.\"},{\"question\":\"What distinguishes the feature-domain JSCC design?\",\"answer\":\"It partitions latent features so that missing features can be semantically recovered, while overall spatial consistency is maintained, improving robustness in distributed erasure settings.\"}]",1784186645,13,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"towards-robust-semantic-video-transmission-over-block-erasure-channels","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/towards-robust-semantic-video-transmission-over-block-erasure-channels/83306/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of the paper?","Question",{"text":75,"@type":76},"The paper aims to make neural video transmission robust to block erasures by combining semantic awareness with joint source-channel coding.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the spatial-domain approach handle block erasures?",{"text":80,"@type":76},"It partitions video frames into blocks and applies uniform erasure handling as well as two-level semantic-guided non-uniform erasure strategies to control robustness at finer granularity.",{"name":82,"@type":73,"acceptedAnswer":83},"What distinguishes the feature-domain JSCC design?",{"text":84,"@type":76},"It partitions latent features so that missing features can be semantically recovered, while overall spatial consistency is maintained, improving robustness in distributed erasure settings.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":21,"slug":137},19,"General","general"]