Referring Video Object Segmentation

There exist previous works [6, 10] that constructed referring segmentation datasets for videos. Gavrilyuk et al. [6] extended the A2D [33] and J-HMDB [9] datasets with natural sentences; the datasets focus on describing the ‘actors’ and ‘actions’ appearing in videos, therefore the instance annotations are limited to only a few object categories corresponding to the dominant ‘actors’ performing a salient ‘action’. Khoreva et al. [10] built a dataset based on DAVIS [25], but the scales are barely sufficient to learn an end-to-end model from scratch Youtube-VOS has 4,519 high-resolution videos with 94 common object categories. Each video has pixel-level instance segmentation annotation at every 5 frames in 30-fps videos, and their durations are around 3 to 6 seconds. We employed Amazon Mechanical Turk to annotate referring expressions. To ensure the quality of the annotations, we selected around 50 turkers after a validation test. Each turker was given a pair of videos, the original video and the mask-overlaid one with the target object highlighted, and was asked to provide a discriminative sentence within 20 words that describes the target object accurately. We collected two kinds of annotations, which describe the highlighted object (1) based on a whole video (Full-video expression) and (2) using only the first frame of the video (First-frame expression). After the initial annotation, we conducted verification and cleaning jobs for all annotations, and dropped objects if an object cannot be localized using language expressions only. The followings are the statistics and analysis of the two annotation types of the dataset after the verification. Full-video expression: Youtube-VOS has 6,459 and 1,063 unique objects in train and validation split, respectively. Among them, we cover 6,388 unique objects in 3,471 videos (6, 388/6, 459 = 98.9%) with 12,913 expressions in train split and 1,063 unique objects in 507 videos (1, 063/1, 063 = 100%) with 2,096 expressions in validation split. On average, each video has 3.8 language expressions and each expression has 10.0 words. First-frame expression: There are 6,006 unique objects in 3,412 videos (6, 006 /6, 459 = 93.0%) with 10,897 expressions in train split and 1,030 unique objects in 507 videos (1, 030/1, 063 = 96.9%) with 1,993 expressions in validation split. The number of annotated objects is lower than that of the full-video expressions because using only the first frame makes annotation more ambiguous and inconsistent and we dropped more annotations during the verification. On average, each video has 3.2 language expressions and each expression has 7.5 words.

MeViS is a large-scale dataset for motion expressions guided video segmentation, which focuses on segmenting objects in video content based on a sentence describing the motion of the objects. The dataset contains numerous motion expressions to indicate target objects in complex environments.

We create a benchmark dataset named ReVOS. This dataset comprises 35,074 pairs of instruction-mask sequences derived from 1,042 diverse videos. In contrast to traditional referring video segmentation datasets, such as Ref-YouTube-VOS and MeViS, which primarily contain explicit short phrases, ReVOS includes text instructions that necessitates a sophisticated understanding of both video content and general world knowledge

This work proposes Long-RVOS, a large-scale benchmark for long-term video object segmentation. Long-RVOS is the first minute-level dataset in the RVOS field, designed to tackle various realistic long-video challenges such as frequent occlusion, disappearance-reappearance, and shot changing. Notably, Long-RVOS offers significantly longer video duration than existing datasets. In addition, it contains the largest number of object classes and mask annotations. The large scale of Long-RVOS supports comprehensive training and evaluation of RVOS models. Finally, we gather 24,689 high-quality descriptions for building Long-RVOS.