Monocular 3D Visual Grounding (Mono3DVG) is an emerging task that locates 3D objects in RGB images using text descriptions with geometric cues. However, existing methods face two key limitations. Firstly, they often over-rely on high-certainty keywords that explicitly identify the target object while neglecting critical spatial descriptions. Secondly, generalized textual features contain both 2D and 3D descriptive information, thereby capturing an additional dimension of details compared to singular 2D or 3D visual features. This characteristic leads to cross-dimensional interference when refining visual features under text guidance. To overcome these challenges, we propose Mono3DVG-EnSD, a novel framework that integrates two key components: the CLIP-Guided Lexical Certainty Adapter (CLIP-LCA) and the Dimension-Decoupled Module (D2M). The CLIP-LCA dynamically masks high-certainty keywords while retaining low-certainty implicit spatial descriptions, thereby forcing the model to develop a deeper understanding of spatial relationships in captions for object localization. Meanwhile, the D2M decouples dimension-specific (2D/3D) textual features from generalized textual features to guide corresponding visual features at same dimension, which mitigates cross-dimensional interference by ensuring dimensionally-consistent cross-modal interactions. Through comprehensive comparisons and ablation studies on the Mono3DRefer dataset, our method achieves state-of-the-art (SOTA) performance across all metrics. Notably, it improves the challenging Far([email protected]) scenario by a significant +13.54%.

Monocular 3D visual grounding is a novel task that aims to locate 3D objects in RGB images using text descriptions with explicit geometry information. Despite the inclusion of geometry details in the text, we observe that the text embeddings are sensitive to the magnitude of numerical values but largely ignore the associated measurement units. For example, simply equidistant mapping the length with unit 'meters' to 'decimeters' or 'centimeters' leads to severe performance degradation, even though the physical length remains equivalent. This observation signifies the weak 3D comprehension of pre-trained language model, which generates misguiding text features to hinder 3D perception. Therefore, we propose to enhance the 3D perception of model on text embeddings and geometry features with two simple and effective methods. Firstly, we introduce a pre-processing method named 3D-text Enhancement (3DTE), which enhances the comprehension of mapping relationships between different units by augmenting the diversity of distance descriptors in text queries. Next, we propose a Text-Guided Geometry Enhancement (TGE) module to further enhance the 3D-text information by projecting the basic text features into geometrically consistent space. These 3D-enhanced text features are then leveraged to precisely guide the attention of geometry features. We evaluate the proposed method through extensive comparisons and ablation studies on the Mono3DRefer dataset. Experimental results demonstrate substantial improvements over previous methods, achieving new state-of-the-art results with a notable accuracy gain of 11.94% in the 'Far' scenario. Our code will be made publicly available.

Given a query image from a camera, person re-identification (Re-ID) can retrieve the images of the same identity from a gallery, the images of which are captured by the other cameras. Therefore, person Re-ID has been widely used in the field of video surveillance. However, person Re-ID still suffers from a series of challenges, such as illumination changes, pose variations, and occlusions. Although the person Re-ID methods based on attention mechanism give an effective and feasible solution for the above challenges, attention mechanism may make a network focus too much on the most salient discriminative features and ignore other potential discriminative features. To solve this problem, we propose a two-level salient feature complementary network (TSFC-Net) to extract the most salient discriminative features and the secondary salient discriminative features of pedestrian images for person Re-ID. Specifically, TSFC-Net first extracts the most salient discriminative features of pedestrian images by embedding the spatial and channel attention modules in the backbone network, and then extracts the secondary salient discriminative features of pedestrian images by a secondary salient feature mining module (SSFM). Since the final features of pedestrian images fuse the most salient discriminative features and the secondary salient discriminative features, TSFC-Net can significantly improve the richness and discrimination capability of pedestrian representations. In addition, we conduct extensive experiments on the Market-1501, DukeMTMC-reID, and CUHK03 data sets, and the experimental results indicate that our TSFC-Net has a better performance compared with most of the state-of-the-art person Re-ID methods.