STVGFormer: Spatio-Temporal Video Grounding with Static-Dynamic Cross-Modal Understanding

In this technical report, we introduce our solution to human-centric spatio-temporal video grounding task. We propose a concise and effective framework named STVGFormer, which models spatiotemporal visual-linguistic dependencies with a static branch and a dynamic branch. The static branch performs cross-modal understanding in a single frame and learns to localize the target object spatially according to intra-frame visual cues like object appearances. The dynamic branch performs cross-modal understanding across multiple frames. It learns to predict the starting and ending time of the target moment according to dynamic visual cues like motions. Both the static and dynamic branches are designed as cross-modal transformers. We further design a novel static-dynamic interaction block to enable the static and dynamic branches to transfer useful and complementary information from each other, which is shown to be effective to improve the prediction on hard cases. Our proposed method achieved 39.6% vIoU and won the first place in the HC-STVG track of the 4th Person in Context Challenge.

Augmented 2D-TAN: A Two-stage Approach for Human-centric Spatio-Temporal Video Grounding

We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task. In the first stage, we propose an Augmented 2D Temporal Adjacent Network (Augmented 2D-TAN) to temporally ground the target moment corresponding to the given description. Primarily, we improve the original 2D-TAN from two aspects: First, a temporal context-aware Bi-LSTM Aggregation Module is developed to aggregate clip-level representations, replacing the original max-pooling. Second, we propose to employ Random Concatenation Augmentation (RCA) mechanism during the training phase. In the second stage, we use pretrained MDETR model to generate per-frame bounding boxes via language query, and design a set of hand-crafted rules to select the best matching bounding box outputted by MDETR for each frame within the grounded moment.

Level-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement

The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i.e.style feature, and the feature representing the invariant semantic content, i.e. content feature. Previous methods separate content feature apart by utilizing it to classify haze image during the training process. However, in this paper we recognize the incompleteness of the content-style disentanglement in such technical routine. The flawed style feature entangled with content information inevitably leads the ill-rendering of the haze images. To address, we propose a self-supervised style regression via stochastic linear interpolation to reduce the content information in style feature. The ablative experiments demonstrate the disentangling completeness and its superiority in level-aware haze image synthesis. Moreover, the generated haze data are applied in the testing generalization of vehicle detectors. Further study between haze-level and detection performance shows that haze has obvious impact on the generalization of the vehicle detectors and such performance degrading level is linearly correlated to the haze-level, which, in turn, validates the effectiveness of the proposed method.