Multiple Object Tracking (MOT) in dynamic and densely populated scenes presents significant challenges due to frequent occlusions, erratic object motion, and identity switches. While recent Transformer-based approaches have successfully leveraged global attention for object detection, most rely on temporal reasoning at the decoder level, leaving encoder-stage modeling underexplored. In this work, we propose an encoder-level temporal reasoning Transformer framework that embeds historical object trajectory information into the encoder stage via a tracklet memory. The encoder module, enhanced by Attention-by-Tracking, enriches visual features with temporal priors, while the decoder leverages Tracking-by-Attention to guide identity association using learned tracklet representations. To further improve temporal consistency and object localization, we introduce a gating-based temporal feature fusion mechanism that adaptively integrates multi-frame features based on cosine similarity. Our method is model-agnostic and can be applied to various Transformer-based MOT frameworks. When integrated into existing models such as TransTrack, MeMOTR, and MOTIP, it yields consistent performance improvements. Extensive experiments on DanceTrack and SportsMOT benchmarks demonstrate that our approach achieves superior tracking performance, including a HOTA score of 76.4 on SportsMOT. These results validate the effectiveness of encoder-level temporal integration and adaptive feature fusion for robust multi-object tracking in real-world scenarios.
We present Mobile-Oriented Video Diffusion (MOVD) framework, the first diffusion-based text-to-video generation framework designed for efficient on-device execution on smartphone-grade hardware without requiring retraining, compression or pruning of the target denoising model. To address the challenges of diffusion-based text-to-video generation on computation- and memory-limited mobile devices, MOVD applies two novel techniques to pretrained video generative models. First, Linear Proportional Leap (LPL) reduces the excessive denoising steps required in video diffusion through an efficient leap-based approach. Second, Temporal Dimension Token Merging (TDTM) reduces the heavy computational load of attention layers by merging consecutive tokens along the temporal dimension. By integrating these techniques with Concurrent Inference with Dynamic Loading (CI-DL), which splits large models into smaller, executable segments for limited memory environments, MOVD allows a text-to-video diffusion generative model to run on an iPhone 15 Pro. We envision the proposed MOVD as a significant first step toward democratizing state-of-the-art generative technologies, enabling video generation on mobile and embedded devices without resource-intensive optimization procedures. Code implementation accessible at the link1.
Domain generalisation aims to develop models that generalise from source domains to unseen target domains. However, most existing methods assume access to source domain data and require additional training, which may not always be practical. We focus on a more flexible and broadly applicable setting, zero-shot domain generalisation, where models generalise without access to source data, target data, or any additional training. In this work, we propose Prefer (prompt-driven feature refinement), a simple and effective approach that enhances the zero-shot domain generalisation ability of vision-language foundation models. Prefer generates a diverse set of textual prompts for each class by imagining domain-specific variations (e.g., "a painting of a cat under a golden sunset with thick brush strokes"), and uses them to probe the model. We evaluate how reliably each feature channel represents a class across domains by measuring two quantities: (1) how strongly the channel aligns with the original class prompt (e.g., "a photo of a cat") across the generated domain-specific prompts, and (2) how stable the channel remains across those prompts, quantified by its variance. Channels that exhibit both high alignment and low variability are selected at inference time to improve class prediction under domain shift. Without any model updates or external data, Prefer achieves consistent improvements across domain generalisation benchmarks, outperforming existing state-of-the-art methods.
Image color enhancement is a key component of ISP pipelines, with 3D LUTs widely adopted for nonlinear color transformations and color refinement. Existing learning-based approaches attempt to learn a global mapping from paired pixel-aligned training samples, but this offers limited control and flexibility for practitioners and restricts adaptation to specific images or scenarios. Moreover, the assumption of pixel-aligned supervision requires costly manual retouching to generate ground-truth references. A practical alternative is to use DSLR images as high-quality references, but the inevitable FoV and PoV variations make pixel-level 3D LUT calibration unreliable. We propose ChameleonTuner1, a novel framework that establishes region-level color correspondences to handle FoV/PoV discrepancies. Unlike prior learning-based 3D LUT methods, the proposed framework defines a dedicated search space for LUT tuning and employs multi-objective search to achieve controllable and interpretable optimization. Extensive experiments across multiple perceptual color metrics demonstrate that our method is effective in subjective scenarios (e.g., DPED) with geometric misalignments, while remaining competitive on standard pixel-aligned benchmarks (e.g., MIT-Adobe FiveK). Our code is available at https://github.com/ZjTan4/ChameleonTuner.git.
Generative artificial intelligence has the potential to improve productivity and transform the production of creative content. However, existing research indicates that image generation models are significantly influenced by biases. This work investigates the inherent biases and language-induced biases present in text-to-image models within the context of occupation-related image generation, complementing established metrics with human preference feedback. We present a comprehensive evaluation of five current text-to-image models: Midjourney v6.1, Stable Diffusion 3 Medium, DALL-E 3, Playground v2.5, and FLUX.1-dev , focusing on gender and ethnicity bias, image quality, and prompt alignment. To facilitate this evaluation, we developed the "Battle-Arena for Fair Image Synthesis" (BAFIS), a platform designed to collect human feedback on bias in generated images. Furthermore, we created a dataset comprising 21,140 synthetic images generated using multilingual prompts, which serves as a basis for our analysis. We further place our results within a broader social context by comparing them to official statistics from the German Federal Employment Agency. Our findings reveal systematic biases in text-to-image models, with established evaluation metrics in partial correlation with subjective user ratings. Thus, our research emphasizes the need for including human preferences to develop fairer and more inclusive text-to-image models.
