相关论文: ViCo: Engaging Video Comment Generation with Human…

Applications designed for entertainment and other non-instrumental purposes are challenging to optimize because the relationships between system parameters and user experience can be unclear. Ideally, we would crowdsource these design…

Modern video diffusion models excel at appearance synthesis but still struggle with physical consistency: objects drift, collisions lack realistic rebound, and material responses seldom match their underlying properties. We present PhyCo, a…

Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames. Creating a benchmark…

The growth of deep learning (DL) relies heavily on huge amounts of labelled data for tasks such as natural language processing and computer vision. Specifically, in image-to-text or image-to-image pipelines, opinion (sentiment) may be…

Video captioning aims to describe events in a video with natural language. In recent years, many works have focused on improving captioning models' performance. However, like other text generation tasks, it risks introducing factual errors…

Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align…

Code comment generation is a crucial task in the field of automatic software development. Most previous neural comment generation systems used an encoder-decoder neural network and encoded only information from source code as input.…

Video generative models show emerging reasoning behaviors. It is essential to ensure that generated events remain causally consistent across frames for reliable deployment, a property we define as reasoning coherence. To bridge the gap in…

Emotional Video Captioning is an emerging task that aims to describe factual content with the intrinsic emotions expressed in videos. The essential of the EVC task is to effectively perceive subtle and ambiguous visual emotional cues during…

Human ratings are currently the most accurate way to assess the quality of an image captioning model, yet most often the only used outcome of an expensive human rating evaluation is a few overall statistics over the evaluation dataset. In…

Comments play an important role within online creative communities because they make it possible to foster the production and improvement of authors' artifacts. We investigate how comment-based communication help shape members' behavior…

The current reward learning from human preferences could be used to resolve complex reinforcement learning (RL) tasks without access to a reward function by defining a single fixed preference between pairs of trajectory segments. However,…

In video captioning task, the best practice has been achieved by attention-based models which associate salient visual components with sentences in the video. However, existing study follows a common procedure which includes a frame-level…

Generating interaction-centric videos, such as those depicting humans or robots interacting with objects, is crucial for embodied intelligence, as they provide rich and diverse visual priors for robot learning, manipulation policy training,…

Stories can have tremendous power -- not only useful for entertainment, they can activate our interests and mobilize our actions. The degree to which a story resonates with its audience may be in part reflected in the emotional journey it…

Automatic hashtag annotation plays an important role in content understanding for microblog posts. To date, progress made in this field has been restricted to phrase selection from limited candidates, or word-level hashtag discovery using…

Existing Causal-Why Video Question Answering (VideoQA) models often struggle with higher-order reasoning, relying on opaque, monolithic pipelines that entangle video understanding, causal inference, and answer generation. These black-box…

How emotions are expressed depends on the context and domain. On X (formerly Twitter), for instance, an author might simply use the hashtag #anger, while in a news headline, emotions are typically written in a more polite, indirect manner.…

Emotions play a key role in human communication and public presentations. Human emotions are usually expressed through multiple modalities. Therefore, exploring multimodal emotions and their coherence is of great value for understanding…

Personalized image generation, where reference images of one or more subjects are used to generate their image according to a scene description, has gathered significant interest in the community. However, such generated images suffer from…