arXiv:2503.15846v4 Announce Type: replace Abstract: Dynamic Scene Graph Generation (DSGG) aims to capture objects and their evolving relations in videos. Despite recent progress, the practicality and...
arXiv:2610.14439v1 Announce Type: cross Abstract: Large multimodal models (LMMs) need to understand how entities move and interact as a scene develops. This requires following the same entities over...
CameraEditor is a new framework that transforms camera-controlled image editing into a temporal sequence prediction problem. By using video diffusion models, it incorporates a geometric perception module and dynamic reference routing to create precise visual references through dynamic panorama cropping. The method also inserts intermediate transition frames to handle large perspective shifts, maintaining content identity and spatial coherence, and is evaluated on a dataset of 5,760 instances with a benchmark of 462 test cases, achieving state‑of‑the‑art performance.
GROME introduces a factorized memory framework for video world models that separates historical evidence into static and dynamic components. It uses local memory retrieval to align static history spatially and injects the factorized memory into models without extra training. Experiments show improved long‑horizon scene persistence and dynamic entity fidelity while maintaining visual quality and controllability.
Event-Causal RAG (EC‑RAG) is a lightweight retrieval‑augmented framework designed for reasoning over ultra‑long and streaming videos. It segments video streams into semantically complete events using a dual visual‑audio sentinel mechanism, representing each event as a State‑Event‑State (SES) structure that captures pre‑event, event, and post‑event states. During question answering, bidirectional graph retrieval accesses relevant predecessor and successor events from a dual vector‑graph memory, and answers are generated using both this structured memory and the corresponding video evidence. The authors also introduce ECV‑1H, an hour‑scale long‑video QA benchmark with over 150 hours of untrimmed video and 1,251 human‑annotated QA pairs, where EC‑RAG achieves significant accuracy gains across multiple video foundation models while maintaining efficient streaming memory usage on a single RTX 5090 GPU.
arXiv:2509. 09151v2 Announce Type: replace-cross Abstract: Research in video understanding has advanced rapidly, driven by increasingly diverse datasets and more powerful model architectures.
arXiv:2608.14835v2 Announce Type: replace Abstract: Dynamic scene graphs (DSGs) capture spatio-temporal interactions across videos as $\langle$subject, predicate, object$\rangle$ triplets, and underp...
Momentum introduces a two-stage pipeline for video world models that uses synchronized multi-camera rigs to represent evolving scenes. The WorldUpdate stage generates shared reference-camera videos as a memory of scene dynamics, while WorldInteract grounds target camera video generation in this memory, ensuring moving objects remain represented outside the field of view. Experiments on CARLA street scenes show a 126.2% improvement in dynamic scene consistency over static image conditioning.
The paper introduces Sora100K, a dataset that captures AI‑Native video creation workflows as structured trajectories rather than isolated clips. It categorizes trajectories into text‑to‑video generation roots, single‑turn editing edges, and multi‑turn editing sequences, annotating each with semantic and operation labels via a VLM. A rigorous construction pipeline ensures accurate source‑to‑edit lineage and intermediate states, and lightweight adaptation on LTX‑2 models demonstrates improved visual quality, multi‑shot generation, and cross‑shot consistency, though multi‑turn editing remains challenging.
STRAND is a new benchmark that tests multimodal large language models’ ability to track objects, their states, and relationships over time in videos. It evaluates intermediate reasoning by breaking queries into sub‑questions and uses Faithful Accuracy to ensure all parts of an answer are correct. The authors also propose an object‑centric framework that builds structured trajectories and shows reduced hallucinations and better temporal consistency compared to existing models.
arXiv:2609.38839v1 Announce Type: new Abstract: Long-horizon video generation requires models to effectively leverage an increasingly long generation history. As the generated history grows, retainin...
arXiv:2607. 08763v1 Announce Type: cross Abstract: Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences.