Zhicheng Zhang(张知诚)

Video prediction is a challenging task due to its nature of uncertainty, especially for forecasting a long period. To model the temporal dynamics, advanced methods benefit from the recent success of diffusion models, and repeatedly refine the predicted future frames with 3D spatiotemporal U-Net. However, there exists a gap between the present and future and the repeated usage of U-Net brings a heavy computation burden. To address this, we propose a diffusion-based video prediction method that predicts future frames by extrapolating the present distribution of features, namely ExtDM. Specifically, our method consists of three components: (i) a motion autoencoder conducts a bijection transformation between video frames and motion cues; (ii) a layered distribution adaptor module extrapolates the present features in the guidance of Gaussian distribution; (iii) a 3D U-Net architecture specialized for jointly fusing guidance and features among the temporal dimension by spatiotemporal-window attention. Extensive experiments on four popular benchmarks covering short- and long-term video prediction verify the effectiveness of ExtDM.

Limited training data is a long-standing problem for video emotion analysis (VEA). Existing works leverage the power of large-scale image datasets for transferring while failing to extract the temporal correlation of affective cues in the video. Inspired by psychology research and empirical theory, we verify that the degree of emotion may vary in different segments of the video, thus introducing the sentiment complementary and emotion intrinsic among temporal segments. Motivated by this, we propose an MAE-style method for learning robust affective representation of videos via masking, termed MART. The method is comprised of emotional lexicon extraction and masked emotion recovery. First, we extract the affective cues of the lexicon and verify the extracted one by computing its matching score with video content. The hierarchical verification strategy is proposed, in terms of sentiment and emotion, to identify the matched cues alongside the temporal dimension. Then, with the verified cues, we propose masked affective modeling to recover temporal emotion distribution. We present temporal affective complementary learning that pulls the complementary part and pushes the intrinsic part of masked multimodal features, for learning robust affective representation. Under the constraint of affective complementary, we leverage cross-modal attention among features to mask the video and recover the degree of emotion among segments. Extensive experiments on three benchmark datasets demonstrate the superiority of our method in video sentiment analysis, video emotion recognition, multimodal sentiment analysis, and multimodal emotion recognition.

Tracking both location and pose of multiple planar objects (MPOT) is of great significance to numerous real-world applications. The greater degree-of-freedom of planar objects compared with common objects makes MPOT far more challenging than well-studied object tracking, especially when occlusion occurs. To address this challenging task, we are inspired by amodal perception that humans jointly track visible and invisible parts of the target, and propose a tracking framework that unifies appearance perception and occlusion reasoning. Specifically, we present a dual branch network to track the visible part of planar objects, including vertexes and mask. Then, we develop an occlusion area localization strategy to infer the invisible part, i.e., the occluded region, followed by a two-stream attention network finally refining the prediction. To alleviate the lack of data in this field, we build the first large-scale benchmark dataset, namely MPOT-3K. It consists of 3,717 planar objects from 356 videos, and contains 148,896 frames together with 687,417 annotations. The collected planar objects have 9 motion patterns and the videos are shot in 6 types of indoor and outdoor scenes. Extensive experiments demonstrate the superiority of our proposed method on the newly developed MPOT-3K as well as other two popular single planar object tracking datasets.

Video sentiment analysis aims to uncover the underlying attitudes of viewers, which has a wide range of applications in real world. Existing works simply classify a video into a single sentimental category, ignoring the fact that sentiment in untrimmed videos may appear in multiple segments with varying lengths and unknown locations. To address this, we propose a challenging task, i.e., Temporal Sentiment Localization (TSL), to find which parts of the video convey sentiment. To systematically investigate fully- and weakly-supervised settings for TSL, we first build a benchmark dataset named TSL-300, which is consisting of 300 videos with a total length of 1,291 minutes. Each video is labeled in two ways, one of which is frame-by-frame annotation for the fully-supervised setting, and the other is single-frame annotation, i.e., only a single frame with strong sentiment is labeled per segment for the weakly-supervised setting. Due to the high cost of labeling a densely annotated dataset, we propose TSL-Net in this work, employing single-frame supervision to localize sentiment in videos. In detail, we generate the pseudo labels for unlabeled frames using a greedy search strategy, and fuse the affective features of both visual and audio modalities to predict the temporal sentiment distribution. Here, a reverse mapping strategy is designed for feature fusion, and a contrastive loss is utilized to maintain the consistency between the original feature and the reverse prediction. Extensive experiments show the superiority of our method against the state-of-the-art approaches.