{"slug": "coanerv-coordinate-aware-token-space-neural-video-representation", "title": "CoANeRV: Coordinate-Aware Token-Space Neural Video Representation", "summary": "Researchers propose CoANeRV, a coordinate-aware token-space framework for amortized video representation that forms compact video tokens in one feed-forward pass and uses a shared coordinate-conditioned decoder, avoiding per-video optimization while improving reconstruction quality over prior feed-forward NeRV and INR baselines and reducing peak memory. The code is available at https://github.com/jialong2023/CoANeRV.", "body_md": "arXiv:2608.13938v1 Announce Type: new\nAbstract: Neural representations for videos (NeRV) have shown strong reconstruction fidelity by storing video-specific information in network weights. However, existing formulations typically require either costly per-video optimization or video-specific weight generation, making it difficult to scale to efficient amortized video representation. We propose CoANeRV, a coordinate-aware token-space framework that adapts the broader token-conditioned neural-field paradigm to amortized video representation. CoANeRV forms compact video tokens in one feed-forward pass and uses a shared coordinate-conditioned decoder to reconstruct continuous spatio-temporal queries, avoiding per-video decoder optimization or generation while retaining coordinate-level reconstruction flexibility. To make token-space reconstruction effective, CoANeRV introduces a coordinate-aware decoding architecture that aligns spatio-temporal queries with video tokens through axis-adaptive positional encoding and temperature-modulated cross-attention. Block-wise coordinate querying further reduces peak attention memory, making high-resolution reconstruction practical. Experiments on diverse video datasets show that CoANeRV consistently improves reconstruction quality over prior feed-forward NeRV and INR baselines, reduces peak memory compared with attention-based coordinate decoders, and provides efficient amortized encoding without per-video optimization. These results support the proposed video-specific combination of feed-forward token formation, spatio-temporal coordinate retrieval, and memory-bounded dense querying. The code is available at https://github.com/jialong2023/CoANeRV.", "url": "https://wpnews.pro/news/coanerv-coordinate-aware-token-space-neural-video-representation", "canonical_source": "https://arxiv.org/abs/2608.13938", "published_at": "2026-08-17 04:00:00+00:00", "updated_at": "2026-08-17 04:11:57.671251+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision", "neural-networks"], "entities": ["CoANeRV", "NeRV", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/coanerv-coordinate-aware-token-space-neural-video-representation", "markdown": "https://wpnews.pro/news/coanerv-coordinate-aware-token-space-neural-video-representation.md", "text": "https://wpnews.pro/news/coanerv-coordinate-aware-token-space-neural-video-representation.txt", "jsonld": "https://wpnews.pro/news/coanerv-coordinate-aware-token-space-neural-video-representation.jsonld"}}