相关论文: Tiger200K: Manually Curated High Visual Quality Vi…
We present TIGERScore, a \textbf{T}rained metric that follows \textbf{I}nstruction \textbf{G}uidance to perform \textbf{E}xplainable, and \textbf{R}eference-free evaluation over a wide spectrum of text generation tasks. Different from other…
Self-supervised features are the cornerstone of modern machine learning systems. They are typically pre-trained on data collections whose construction and curation typically require extensive human effort. This manual process has some…
Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervised feature learning have focused on either small or highly…
A major challenge in text-video and text-audio retrieval is the lack of large-scale training data. This is unlike image-captioning, where datasets are in the order of millions of samples. To close this gap we propose a new video mining…
Generating video descriptions in natural language (a.k.a. video captioning) is a more challenging task than image captioning as the videos are intrinsically more complicated than images in two aspects. First, videos cover a broader range of…
The demand for producing short-form videos for sharing on social media platforms has experienced significant growth in recent times. Despite notable advancements in the fields of video summarization and highlight detection, which can create…
The development of video game streaming has grown rapidly, with major platforms such as YouTube and Twitch using different codecs. To support quality assessment models that work consistently across any codec, it is necessary to have access…
Ultra-high-resolution image synthesis holds significant potential, yet remains an underexplored challenge due to the absence of standardized benchmarks and computational constraints. In this paper, we establish Aesthetic-4K, a meticulously…
The rapid increase in user-generated-content (UGC) videos calls for the development of effective video quality assessment (VQA) algorithms. However, the objective of the UGC-VQA problem is still ambiguous and can be viewed from two…
The recent advancements in Text-to-Video Artificial Intelligence Generated Content (AIGC) have been remarkable. Compared with traditional videos, the assessment of AIGC videos encounters various challenges: visual inconsistency that defy…
Large language models (LLMs) often struggle with visualization tasks like plotting diagrams, charts, where success depends on both code correctness and visual semantics. Existing instruction-tuning datasets lack execution-grounded…
Recent advances in Generative AI (GenAI) have led to significant improvements in the quality of generated visual content. As AI-generated visual content becomes increasingly indistinguishable from real content, the challenge of detecting…
With the rapid development of generative models, Artificial Intelligence-Generated Contents (AIGC) have exponentially increased in daily lives. Among them, Text-to-Video (T2V) generation has received widespread attention. Though many T2V…
With the rapid advancements in AI-Generated Content (AIGC), AI-Generated Images (AIGIs) have been widely applied in entertainment, education, and social media. However, due to the significant variance in quality among different AIGIs, there…
As Artificial Intelligence applications expand, the evaluation of models faces heightened scrutiny. Ensuring public readiness requires evaluation datasets, which differ from training data by being disjoint and ethically sourced in…
Perception-based image analysis technologies can be used to help visually impaired people take better quality pictures by providing automated guidance, thereby empowering them to interact more confidently on social media. The photographs…
Recent advances in Multimodal Large Language Models (MLLMs) have introduced a paradigm shift for Image Quality Assessment (IQA) from unexplainable image quality scoring to explainable IQA, demonstrating practical applications like quality…
Synthetic image datasets offer unmatched advantages for designing and evaluating deep neural networks: they make it possible to (i) render as many data samples as needed, (ii) precisely control each scene and yield granular ground truth…
The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data. While existing datasets have covered basic tasks like style transfer and…
As sharing images in an instant message is a crucial factor, there has been active research on learning an image-text multi-modal dialogue models. However, training a well-generalized multi-modal dialogue model remains challenging due to…