相关论文: COMPOSER: Compositional Reasoning of Group Activit…
Existing research on action recognition treats activities as monolithic events occurring in videos. Recently, the benefits of formulating actions as a combination of atomic-actions have shown promise in improving action understanding with…
To apply neural sequence models such as the Transformers to music generation tasks, one has to represent a piece of music by a sequence of tokens drawn from a finite set of pre-defined vocabulary. Such a vocabulary usually involves tokens…
Video captioning works on the two fundamental concepts, feature detection and feature composition. While modern day transformers are beneficial in composing features, they lack the fundamental problems of selecting and understanding of the…
Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations. In this paper, we study the compositionality of action by looking into the…
The visual world is fundamentally compositional. Visual scenes are defined by the composition of objects and their relations. Hence, it is essential for computer vision systems to reflect and exploit this compositionality to achieve robust…
Group activity recognition is the task of understanding the activity conducted by a group of people as a whole in a multi-person video. Existing models for this task are often impractical in that they demand ground-truth bounding box labels…
Image composition involves seamlessly integrating given objects into a specific visual context. Current training-free methods rely on composing attention weights from several samplers to guide the generator. However, since these weights are…
Compositional scene reconstruction seeks to create object-centric representations rather than holistic scenes from real-world videos, which is natively applicable for simulation and interaction. Conventional compositional reconstruction…
Robotic agents performing domestic chores by natural language directives are required to master the complex job of navigating environment and interacting with objects in the environments. The tasks given to the agents are often composite…
Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability in learning symbolic…
Symbolic music generation aims to generate music scores automatically. A recent trend is to use Transformer or its variants in music generation, which is, however, suboptimal, because the full attention cannot efficiently model the…
We present FashionComposer for compositional fashion image generation. Unlike previous methods, FashionComposer is highly flexible. It takes multi-modal input (i.e., text prompt, parametric human model, garment image, and face image) and…
Compositional understanding is crucial for human intelligence, yet it remains unclear whether contemporary vision models exhibit it. The dominant machine learning paradigm is built on the premise that scaling data and model sizes will…
Language-guided navigation is a cornerstone of embodied AI, enabling agents to interpret language instructions and navigate complex environments. However, expert-provided instructions are limited in quantity, while synthesized annotations…
Composition matters during the photo-taking process, yet many casual users struggle to frame well-composed images. To provide composition guidance, we introduce PhotoFramer, a multi-modal composition instruction framework. Given a poorly…
Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky…
Compositionality is a cognitive mechanism that allows humans to systematically combine known concepts in novel ways. This study demonstrates how artificial neural agents acquire and utilize compositional generalization to describe…
Learning compositional representation is a key aspect of object-centric learning as it enables flexible systematic generalization and supports complex visual reasoning. However, most of the existing approaches rely on auto-encoding…
It is well known that most of the conventional video question answering (VideoQA) datasets consist of easy questions requiring simple reasoning processes. However, long videos inevitably contain complex and compositional semantic structures…
Compositional generalization is a basic and essential intellective capability of human beings, which allows us to recombine known parts readily. However, existing neural network based models have been proven to be extremely deficient in…