Progressive Scaling Visual Object Tracking

In this work, we propose a progressive scaling training strategy for visual object tracking, systematically analyzing the influence of training data volume, model size, and input resolution on tracking performance. Our empirical study reveals that while scaling each factor leads to significant improvements in tracking accuracy, naive training suffers from suboptimal optimization and limited iterative refinement. To address this issue, we introduce DT-Training, a progressive scaling framework that integrates small teacher transfer and dual-branch alignment to maximize model potential. The resulting scaled tracker consistently outperforms state-of-the-art methods across multiple benchmarks, demonstrating strong generalization and transferability of the proposed method. Furthermore, we validate the broader applicability of our approach to additional tasks, underscoring its versatility beyond tracking.

SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models

Achieving fine-grained spatio-temporal understanding in videos remains a major challenge for current Video Large Multimodal Models (Video LMMs). Addressing this challenge requires mastering two core capabilities: video referring understanding, which captures the semantics of video regions, and video grounding, which segments object regions based on natural language descriptions. However, most existing approaches tackle these tasks in isolation, limiting progress toward unified, referentially grounded video interaction. We identify a key bottleneck in the lack of high-quality, unified video instruction data and a comprehensive benchmark for evaluating referentially grounded video chat. To address these challenges, we contribute in three core aspects: dataset, model, and benchmark. First, we introduce SAMA-239K, a large-scale dataset comprising 15K videos specifically curated to enable joint learning of video referring understanding, grounding, and multi-turn video chat. Second, we propose the SAMA model, which incorporates a versatile spatio-temporal context aggregator and a Segment Anything Model to jointly enhance fine-grained video comprehension and precise grounding capabilities. Finally, we establish SAMA-Bench, a meticulously designed benchmark consisting of 5,067 questions from 522 videos, to comprehensively evaluate the integrated capabilities of Video LMMs in multi-turn, spatio-temporal referring understanding and grounded dialogue. Extensive experiments and benchmarking results show that SAMA not only achieves strong performance on SAMA-Bench but also sets a new state-of-the-art on general grounding benchmarks, while maintaining highly competitive performance on standard visual understanding benchmarks.

Open-set Anomaly Segmentation in Complex Scenarios

Precise segmentation of out-of-distribution (OoD) objects, herein referred to as anomalies, is crucial for the reliable deployment of semantic segmentation models in open-set, safety-critical applications, such as autonomous driving. Current anomalous segmentation benchmarks predominantly focus on favorable weather conditions, resulting in untrustworthy evaluations that overlook the risks posed by diverse meteorological conditions in open-set environments, such as low illumination, dense fog, and heavy rain. To bridge this gap, this paper introduces the ComsAmy, a challenging benchmark specifically designed for open-set anomaly segmentation in complex scenarios. ComsAmy encompasses a wide spectrum of adverse weather conditions, dynamic driving environments, and diverse anomaly types to comprehensively evaluate the model performance in realistic open-world scenarios. Our extensive evaluation of several state-of-the-art anomalous segmentation models reveals that existing methods demonstrate significant deficiencies in such challenging scenarios, highlighting their serious safety risks for real-world deployment. To solve that, we propose a novel energy-entropy learning (EEL) strategy that integrates the complementary information from energy and entropy to bolster the robustness of anomaly segmentation under complex open-world environments. Additionally, a diffusion-based anomalous training data synthesizer is proposed to generate diverse and high-quality anomalous images to enhance the existing copy-paste training data synthesizer. Extensive experimental results on both public and ComsAmy benchmarks demonstrate that our proposed diffusion-based synthesizer with energy and entropy learning (DiffEEL) serves as an effective and generalizable plug-and-play method to enhance existing models, yielding an average improvement of around 4.96% in $\rm{AUPRC}$ and 9.87% in $\rm{FPR}_{95}$.

PVUW 2025 Challenge Report: Advances in Pixel-level Understanding of Complex Videos in the Wild

This report provides a comprehensive overview of the 4th Pixel-level Video Understanding in the Wild (PVUW) Challenge, held in conjunction with CVPR 2025. It summarizes the challenge outcomes, participating methodologies, and future research directions. The challenge features two tracks: MOSE, which focuses on complex scene video object segmentation, and MeViS, which targets motion-guided, language-based video segmentation. Both tracks introduce new, more challenging datasets designed to better reflect real-world scenarios. Through detailed evaluation and analysis, the challenge offers valuable insights into the current state-of-the-art and emerging trends in complex video segmentation. More information can be found on the workshop website: https://pvuw.github.io/.

Exploiting Temporal State Space Sharing for Video Semantic Segmentation

Video semantic segmentation (VSS) plays a vital role in understanding the temporal evolution of scenes. Traditional methods often segment videos frame-by-frame or in a short temporal window, leading to limited temporal context, redundant computations, and heavy memory requirements. To this end, we introduce a Temporal Video State Space Sharing (TV3S) architecture to leverage Mamba state space models for temporal feature sharing. Our model features a selective gating mechanism that efficiently propagates relevant information across video frames, eliminating the need for a memory-heavy feature pool. By processing spatial patches independently and incorporating shifted operation, TV3S supports highly parallel computation in both training and inference stages, which reduces the delay in sequential state space processing and improves the scalability for long video sequences. Moreover, TV3S incorporates information from prior frames during inference, achieving long-range temporal coherence and superior adaptability to extended sequences. Evaluations on the VSPW and Cityscapes datasets reveal that our approach outperforms current state-of-the-art methods, establishing a new standard for VSS with consistent results across long video sequences. By achieving a good balance between accuracy and efficiency, TV3S shows a significant advancement in spatiotemporal modeling, paving the way for efficient video analysis. The code is publicly available at https://github.com/Ashesham/TV3S.git.

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge

Monocular Depth Estimation (MDE) has emerged as a pivotal task in computer vision, supporting numerous real-world applications. However, deploying accurate depth estimation models on resource-limited edge devices, especially Application-Specific Integrated Circuits (ASICs), is challenging due to the high computational and memory demands. Recent advancements in foundational depth estimation deliver impressive results but further amplify the difficulty of deployment on ASICs. To address this, we propose QuartDepth which adopts post-training quantization to quantize MDE models with hardware accelerations for ASICs. Our approach involves quantizing both weights and activations to 4-bit precision, reducing the model size and computation cost. To mitigate the performance degradation, we introduce activation polishing and compensation algorithm applied before and after activation quantization, as well as a weight reconstruction method for minimizing errors in weight quantization. Furthermore, we design a flexible and programmable hardware accelerator by supporting kernel fusion and customized instruction programmability, enhancing throughput and efficiency. Experimental results demonstrate that our framework achieves competitive accuracy while enabling fast inference and higher energy efficiency on ASICs, bridging the gap between high-performance depth estimation and practical edge-device applicability. Code: https://github.com/shawnricecake/quart-depth

Free-Form Motion Control: A Synthetic Video Generation Dataset with Controllable Camera and Object Motions

Controlling the movements of dynamic objects and the camera within generated videos is a meaningful yet challenging task. Due to the lack of datasets with comprehensive motion annotations, existing algorithms can not simultaneously control the motions of both camera and objects, resulting in limited controllability over generated contents. To address this issue and facilitate the research in this field, we introduce a Synthetic Dataset for Free-Form Motion Control (SynFMC). The proposed SynFMC dataset includes diverse objects and environments and covers various motion patterns according to specific rules, simulating common and complex real-world scenarios. The complete 6D pose information facilitates models learning to disentangle the motion effects from objects and the camera in a video. To validate the effectiveness and generalization of SynFMC, we further propose a method, Free-Form Motion Control (FMC). FMC enables independent or simultaneous control of object and camera movements, producing high-fidelity videos. Moreover, it is compatible with various personalized text-to-image (T2I) models for different content styles. Extensive experiments demonstrate that the proposed FMC outperforms previous methods across multiple scenarios.

Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension

In this work, we address the challenging task of Generalized Referring Expression Comprehension (GREC). Compared to the classic Referring Expression Comprehension (REC) that focuses on single-target expressions, GREC extends the scope to a more practical setting by further encompassing no-target and multi-target expressions. Existing REC methods face challenges in handling the complex cases encountered in GREC, primarily due to their fixed output and limitations in multi-modal representations. To address these issues, we propose a Hierarchical Alignment-enhanced Adaptive Grounding Network (HieA2G) for GREC, which can flexibly deal with various types of referring expressions. First, a Hierarchical Multi-modal Semantic Alignment (HMSA) module is proposed to incorporate three levels of alignments, including word-object, phrase-object, and text-image alignment. It enables hierarchical cross-modal interactions across multiple levels to achieve comprehensive and robust multi-modal understanding, greatly enhancing grounding ability for complex cases. Then, to address the varying number of target objects in GREC, we introduce an Adaptive Grounding Counter (AGC) to dynamically determine the number of output targets. Additionally, an auxiliary contrastive loss is employed in AGC to enhance object-counting ability by pulling in multi-modal features with the same counting and pushing away those with different counting. Extensive experimental results show that HieA2G achieves new state-of-the-art performance on the challenging GREC task and also the other 4 tasks, including REC, Phrase Grounding, Referring Expression Segmentation (RES), and Generalized Referring Expression Segmentation (GRES), demonstrating the remarkable superiority and generalizability of the proposed HieA2G.

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

Diffusion Transformers have emerged as the preeminent models for a wide array of generative tasks, demonstrating superior performance and efficacy across various applications. The promising results come at the cost of slow inference, as each denoising step requires running the whole transformer model with a large amount of parameters. In this paper, we show that performing the full computation of the model at each diffusion step is unnecessary, as some computations can be skipped by lazily reusing the results of previous steps. Furthermore, we show that the lower bound of similarity between outputs at consecutive steps is notably high, and this similarity can be linearly approximated using the inputs. To verify our demonstrations, we propose the \textbf{LazyDiT}, a lazy learning framework that efficiently leverages cached results from earlier steps to skip redundant computations. Specifically, we incorporate lazy learning layers into the model, effectively trained to maximize laziness, enabling dynamic skipping of redundant computations. Experimental results show that LazyDiT outperforms the DDIM sampler across multiple diffusion transformer models at various resolutions. Furthermore, we implement our method on mobile devices, achieving better performance than DDIM with similar latency.

Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models

Instruction tuning constitutes a prevalent technique for tailoring Large Vision Language Models (LVLMs) to meet individual task requirements. To date, most of the existing approaches are confined to single-task adaptation, whereas the requirements in real-world scenarios are inherently varied and continually evolving. Thus an ideal LVLM should sustain continual instruction tuning in the face of stream-task distributions (i.e., different domains, emerging capabilities, and new datasets) while minimizing the forgetting of previously acquired knowledge. To achieve this, we propose a new benchmark for COntinuAl inStruction Tuning on LVLMs (COAST), which encompasses the aforementioned domain-incremental, capability-incremental, and dataset-incremental configurations. In terms of methodology, we propose Continual LLaVA, a rehearsal-free method tailored for continual instruction tuning in LVLMs. To circumvent the additional overhead associated with experience replay, we freeze LVLMs and construct the dual increment embeddings for each input instruction to facilitate parameter-efficient tuning. Specifically, the increment embeddings can be decomposed into two principal components: 1) intrinsic increment embeddings to encode task-specific characteristics. To achieve this, we set up a low-rank pool containing candidate embeddings, from which we select the relevant ones based on their similarity with the user instructions; 2) contextual increment embeddings to investigate the inter-dependencies across tasks. In this regard, the low-rank embeddings chosen in the previous tasks are aggregated via learnable weighted sum to provide complementary hints. Extensive experiments indicate that the proposed Continual LLaVA outperforms previous methods by significantly reducing the forgetting during the continual instruction tuning process.