Learning Object State Changes in Videos: An Open-World Perspective
This work addresses the limitation of current video understanding methods that are confined to a closed vocabulary, enabling generalization to unknown objects, which is incremental but important for practical applications.
The paper tackles the problem of localizing object state changes in videos in an open-world setting, where objects may not have been seen during training, and introduces VidOSC, a method that uses text and vision-language models for supervision and abstracts shared state representations, achieving effective results in both closed-world and open-world scenarios.
Object State Changes (OSCs) are pivotal for video understanding. While humans can effortlessly generalize OSC understanding from familiar to unknown objects, current approaches are confined to a closed vocabulary. Addressing this gap, we introduce a novel open-world formulation for the video OSC problem. The goal is to temporally localize the three stages of an OSC -- the object's initial state, its transitioning state, and its end state -- whether or not the object has been observed during training. Towards this end, we develop VidOSC, a holistic learning approach that: (1) leverages text and vision-language models for supervisory signals to obviate manually labeling OSC training data, and (2) abstracts fine-grained shared state representations from objects to enhance generalization. Furthermore, we present HowToChange, the first open-world benchmark for video OSC localization, which offers an order of magnitude increase in the label space and annotation volume compared to the best existing benchmark. Experimental results demonstrate the efficacy of our approach, in both traditional closed-world and open-world scenarios.