Our solution is to unleash the power of multimodal vision-language (VL) tracking, simply using ConvNets.

Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOTAs). However, this advancement accompanies by larger training data and longer training period, making tracking increasingly expensive. In this paper, we demonstrate that the Transformer-reliance is not necessary and the pure ConvNets are still competitive and even better yet more economical and friendly in achieving SOTA tracking. Our solution is to unleash the power of multimodal vision-language (VL) tracking, simply using ConvNets. The essence lies in learning novel unified-adaptive VL representations with our modality mixer (ModaMixer) and asymmetrical ConvNet search. We show that our unified-adaptive VL representation, learned purely with the ConvNets, is a simple yet strong alternative to Transformer visual features, by unbelievably improving a CNN-based Siamese tracker by 14.5% in SUC on challenging LaSOT (50.7%$\rightarrow$65.2%),

Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOT As).

Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOTAs). However, this advancement accompanies by larger training data and longer training period, making tracking increasingly expensive. In this paper, we demonstrate that the Transformer-reliance is not necessary and the pure ConvNets are still competitive and even better yet more economical and friendly in achieving SOTA tracking. Our solution is to unleash the power of multimodal vision-language (VL) tracking, simply using ConvNets. The essence lies in learning novel unified-adaptive VL representations with our modality mixer (ModaMixer) and asymmetrical ConvNet search.

Vision-language models (VLMs) mainly rely on contrastive training to learn general-purpose representations of images and captions. We focus on the situation when one image is associated with several captions, each caption containing both information shared among all captions and unique information per caption about the scene depicted in the image. In such cases, it is unclear whether contrastive losses are sufficient for learning task-optimal representations that contain all the information provided by the captions or whether the contrastive learning setup encourages the learning of a simple shortcut that minimizes contrastive loss. We introduce synthetic shortcuts for vision-language: a training and evaluation framework where we inject synthetic shortcuts into image-text data. We show that contrastive VLMs trained from scratch or fine-tuned with data containing these synthetic shortcuts mainly learn features that represent the shortcut. Hence, contrastive losses are not sufficient to learn task-optimal representations, i.e., representations that contain all task-relevant information shared between the image and associated captions. We examine two methods to reduce shortcut learning in our training and evaluation framework: (i) latent target decoding and (ii) implicit feature modification. We show empirically that both methods improve performance on the evaluation task, but only partly reduce shortcut learning when training and evaluating with our shortcut learning framework. Hence, we show the difficulty and challenge of our shortcut learning framework for contrastive vision-language representation learning.

Within the multimodal field, the key to integrating vision and language lies in establishing a good alignment strategy. Recently, benefiting from the success of self-supervised learning, significant progress has been made in multimodal semantic representation based on pre-trained models for vision and language. However, there is still room for improvement in visual semantic representation. The lack of spatial semantic coherence and vulnerability to noise makes it challenging for current pixel or patch-based methods to accurately extract complex scene boundaries. To this end, this paper develops superpixel as a comprehensive compact representation of learnable image data, which effectively reduces the number of visual primitives for subsequent processing by clustering perceptually similar pixels. To mine more precise topological relations, we propose a Multiscale Difference Graph Convolutional Network (MDGCN). It parses the entire image as a fine-to-coarse hierarchical structure of constituent visual patterns, and captures multiscale features by progressively merging adjacent superpixels as graph nodes. Moreover, we predict the differences between adjacent nodes through the graph structure, facilitating key information aggregation of graph nodes to reason actual semantic relations. Afterward, we design a multi-level fusion rule in a bottom-up manner to avoid understanding deviation by learning complementary spatial information at different regional scales. Our proposed method can be well applied to multiple downstream task learning. Extensive experiments demonstrate that our method is competitive with other state-of-the-art methods in visual reasoning. Our code will be released upon publication.