https://mm.telecom-paris.fr/research/Recent content in Research on Multimedia Team — LTCI, Télécom ParisHugoen-ushttps://mm.telecom-paris.fr/research/video-coding/Mon, 01 Jan 0001 00:00:00 +0000https://mm.telecom-paris.fr/research/video-coding/Conventional and learning-based video compression — codecs, rate–distortion, and the boundary between hand-designed and neural pipelines.https://mm.telecom-paris.fr/research/rich-media-scenes/Mon, 01 Jan 0001 00:00:00 +0000https://mm.telecom-paris.fr/research/rich-media-scenes/Representing complex scenes with multiple media, layouts, and interactions — beyond a single video stream.https://mm.telecom-paris.fr/research/content-adaptation/Mon, 01 Jan 0001 00:00:00 +0000https://mm.telecom-paris.fr/research/content-adaptation/Adapting multimedia content to networks, devices, and users — quality of experience under constraints.https://mm.telecom-paris.fr/research/distribution-networks/Mon, 01 Jan 0001 00:00:00 +0000https://mm.telecom-paris.fr/research/distribution-networks/Transport, orchestration, and protocols for delivering multimedia at scale.https://mm.telecom-paris.fr/research/frugal-ai/Mon, 01 Jan 0001 00:00:00 +0000https://mm.telecom-paris.fr/research/frugal-ai/Pruning, quantization, low-rank methods, and other tools to make deep models small enough to deploy.https://mm.telecom-paris.fr/research/geometric-deep-learning/Mon, 01 Jan 0001 00:00:00 +0000https://mm.telecom-paris.fr/research/geometric-deep-learning/Learning on graphs, manifolds, and structured domains — where the geometry of the data shapes the architecture.https://mm.telecom-paris.fr/research/multimodal-learning/Mon, 01 Jan 0001 00:00:00 +0000https://mm.telecom-paris.fr/research/multimodal-learning/Joint models for vision, language, and beyond — alignment, fusion, and grounded reasoning.