Related papers: SPATIALALIGN: Aligning Dynamic Spatial Relationshi…
Text-to-video (T2V) synthesis has advanced rapidly, yet current evaluation metrics primarily capture visual quality and temporal consistency, offering limited insight into how synthetic videos perform in downstream tasks such as…
Empowered by large-scale training, vision-language models (VLMs) achieve strong image and video understanding, yet their ability to perform spatial reasoning in both static scenes and dynamic videos remains limited. Recent advances try to…
Although video multimodal large language models (video MLLMs) have achieved substantial progress in video captioning tasks, it remains challenging to adjust the focal emphasis of video captions according to human preferences. To address…
Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models…
Video Temporal Grounding (VTG) aims to localize the video segment that corresponds to a natural language query, which requires a comprehensive understanding of complex temporal dynamics. Existing Vision-LMMs typically perceive temporal…
While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures…
Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…
While video generation models excel at producing high-quality monocular videos, generating 3D stereoscopic and spatial videos for immersive applications remains an underexplored challenge. We present a pose-free and training-free method…
This study introduces an enhanced approach to video super-resolution by extending ordinary Single-Image Super-Resolution (SISR) Super-Resolution Generative Adversarial Network (SRGAN) structure to handle spatio-temporal data. While SRGAN…
This paper introduces V2A-DPO, a novel Direct Preference Optimization (DPO) framework tailored for flow-based video-to-audio generation (V2A) models, incorporating key adaptations to effectively align generated audio with human preferences.…
Spatial reasoning in vision language models (VLMs) remains fragile when semantics hinge on subtle temporal or geometric cues. We introduce a synthetic benchmark that probes two complementary skills: situational awareness (recognizing…
Recent advances in LVLMs have improved vision-language understanding, but they still struggle with spatial perception, limiting their ability to reason about complex 3D scenes. Unlike previous approaches that incorporate 3D representations…
The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly based on the video diffusion transformer (vDiT), however, they…
Recent advancements of generative AI have significantly promoted content creation and editing, where prevailing studies further extend this exciting progress to video editing. In doing so, these studies mainly transfer the inherent motion…
Vision-language-action (VLA) models have recently shown strong potential in enabling robots to follow language instructions and execute precise actions. However, most VLAs are built upon vision-language models pretrained solely on 2D data,…
Recent advances in video-large language models (Video-LLMs) have led to significant progress in video understanding. Current preference optimization methods often rely on proprietary APIs or human-annotated captions to generate preference…
In this paper, we propose a spatial-temporal relational reasoning networks (STRRN) approach to investigate the problem of omni-supervised face alignment in videos. Unlike existing fully supervised methods which rely on numerous annotations…
Generative AI models, particularly Text-to-Video (T2V) systems, offer a promising avenue for transforming science education by automating the creation of engaging and intuitive visual explanations. In this work, we take a first step toward…
Zero-shot video moment retrieval (ZVMR) is the task of localizing a temporal moment within an untrimmed video using a natural language query without relying on task-specific training data. The primary challenge in this setting lies in the…
We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from…