Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect of PNG is the visual-linguistic interaction between image and caption. The previous two-stage method aggregates visual contexts from offline-generated mask proposals to phrase features, which tend to be noisy and fragmentary. The recent one-stage method aggregates only pixel contexts from image features to phrase features, which may incur semantic misalignment due to lacking object priors. To realize more comprehensive visual-linguistic interaction, we propose to enrich phrases with coupled pixel and object contexts by designing a Phrase-Pixel-Object Transformer Decoder (PPO-TD), where both fine-grained part details and coarse-grained entity clues are aggregated to phrase features. In addition, we also propose a PhraseObject Contrastive Loss (POCL) to pull closer the matched phrase-object pairs and push away unmatched ones for aggregating more precise object contexts from more phrase-relevant object tokens. Extensive experiments on the PNG benchmark show our method achieves new state-of-the-art performance with large margins.

通过设计Phrase-Pixel-Object Transformer Decoder（PPO-TD）来丰富与像素和物体上下文相关的短语特征，并提出Phrase-Object Contrastive Loss（POCL）从短语相关的物体标记中聚合更精确的物体上下文，这使得我们的方法在Panoptic narrative grounding基准测试中取得了新的最先进性能。

通过像素和物体背景来丰富短语以用于全景叙事引导