FeVOS: Foresight Expression Video Object Segmentation
This work addresses the need for predictive spatio-temporal reasoning in video object segmentation, enabling models to answer future-oriented queries for applications like egocentric vision.
The paper introduces Foresight Expression Video Object Segmentation (FeVOS), a new task requiring models to predict masks of objects in observed frames based on queries about future events. They created a dataset with 968 clips and 14,525 expressions, and trained FeVOS-R1, which achieves state-of-the-art performance on FeVOS and generalizes to existing benchmarks.
Existing Referring Video Object Segmentation tasks focus on referring expressions describing events, actions or appearances of relevant objects within the observed frames, lacking evaluation in scenarios that require pre-decisive spatio-temporal reasoning, thereby limiting their applicability. To address this, we propose Foresight Expression Video Object Segmentation, a task that queries future events in upcoming video segments and requires masks of the objects in the observed frames as visual answers. For example, in ego-centric scenes, the question "What tool will be used?" demands reasoning over spatio-temporal cues to predict the masks of the next tool to be used, which helps with the understanding of future actions and decisions. To support this task, we introduce FeVOS, a dataset with 968 video clips, 14,525 foresight expressions, and 2,904 chain-of-thought annotations to provide explicit and interpretable reasoning steps. We further develop FeVOS-R1, an MLLM-based model trained on our dataset via a two-stage pipeline of supervised fine-tuning and reinforcement learning. FeVOS-R1 not only achieves state-of-the-art performance on FeVOS, but also demonstrates strong generalization to existing RVOS benchmarks. We hope this work can inspire more research on predictive reasoning in video perception.