Related papers: MiraData: A Large-Scale Video Dataset with Long Du…
Precise video retrieval requires multi-modal correlations to handle unseen vocabulary and scenes, becoming more complex for lengthy videos where models must perform effectively without prior training on a specific dataset. We introduce a…
As a prominent subfield of Artificial Intelligence Generated Content (AIGC), video generation has achieved notable advancements in recent years. The introduction of Sora-alike models represents a pivotal breakthrough in video generation…
In this paper, we propose a novel method for video moment retrieval (VMR) that achieves state of the arts (SOTA) performance on R@1 metrics and surpassing the SOTA on the high IoU metric (R@1, IoU=0.7). First, we propose to use a multi-head…
Compared to images, videos better reflect real-world acquisition and possess valuable temporal cues. However, existing multi-sensor fusion research predominantly integrates complementary context from multiple images rather than videos due…
Given the rapid improvement of the detectors at high-energy physics experiments, the need for real-time data monitoring systems has become imperative. The significance of these systems lies in their ability to display experiment status,…
We conducted a large-scale subjective study of the perceptual quality of User-Generated Mobile Video Content on a set of mobile-originated videos obtained from the Indian social media platform ShareChat. The content viewed by volunteer…
Video diffusion transformers have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention over high-dimensional video sequences. Recent acceleration…
We introduce Long-VITA, a simple yet effective large multi-modal model for long-context visual-language understanding tasks. It is adept at concurrently processing and analyzing modalities of image, video, and text over 4K frames or 1M…
With the fast development of artificial intelligence and short videos, emotion recognition in short videos has become one of the most important research topics in human-computer interaction. At present, most emotion recognition methods…
The performance model of an application can pro- vide understanding about its runtime behavior on particular hardware. Such information can be analyzed by developers for performance tuning. However, model building and analyzing is…
Efficient video-language modeling should consider the computational cost because of a large, sometimes intractable, number of video frames. Parametric approaches such as the attention mechanism may not be ideal since its computational cost…
Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal coherence, their dynamics are often constrained by the continuous nature of their training data.…
Humans can easily describe what they see in a coherent way and at varying level of detail. However, existing approaches for automatic video description are mainly focused on single sentence generation and produce descriptions at a fixed…
Temporal realism remains a central weakness of current generative video models, as most evaluation metrics prioritize spatial appearance and offer limited sensitivity to motion. We introduce a scalable, model-agnostic framework that…
Story visualization requires generating sequential imagery that aligns semantically with evolving narratives while maintaining rigorous consistency in character identity and visual style. However, existing methodologies often struggle with…
Sora has unveiled the immense potential of the Diffusion Transformer (DiT) architecture in single-scene video generation. However, the more challenging task of multi-scene video generation, which offers broader applications, remains…
Despite recent advances in 3D human motion generation (MoGen) on standard benchmarks, existing text-to-motion models still face a fundamental bottleneck in their generalization capability. In contrast, adjacent generative fields, most…
Video captions play a crucial role in text-to-video generation tasks, as their quality directly influences the semantic coherence and visual fidelity of the generated videos. Although large vision-language models (VLMs) have demonstrated…
Real-world long video understanding requires models to perform continuous tracking, information integration and memory retention over massive temporal spans within extreme video durations. Mastering this intense cognitive load constitutes…
We study the problem of synthesizing a long-term dynamic video from only a single image. This is challenging since it requires consistent visual content movements given large camera motions. Existing methods either hallucinate inconsistent…